diff --git a/model-00001-of-00136.safetensors b/model-00001-of-00136.safetensors deleted file mode 100644 index c44ded559991424c15dd4da7f49c6be6edb5ac46..0000000000000000000000000000000000000000 --- a/model-00001-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d6a15d616c0c7a65e7752aaf3f3bff189a3f9d4eb28be265fb32a6accc9f9c71 -size 3622335840 diff --git a/model-00002-of-00136.safetensors b/model-00002-of-00136.safetensors deleted file mode 100644 index 195d5ad579bf0f9e09ccc85f28b97b9fd8324f7d..0000000000000000000000000000000000000000 --- a/model-00002-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a86675330958c8018b1be09e6bfd66569127b3464c0c7c0111419045dcbc528c -size 4376532008 diff --git a/model-00003-of-00136.safetensors b/model-00003-of-00136.safetensors deleted file mode 100644 index 3f993e15160103ed1935ae716024e45de27aed07..0000000000000000000000000000000000000000 --- a/model-00003-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:18eca4e9559df276a095077ed50320d440836cde2048f117acdf9bab667f42e5 -size 4376532008 diff --git a/model-00004-of-00136.safetensors b/model-00004-of-00136.safetensors deleted file mode 100644 index 75a26ccacc8d1e61d2a03852ac2fb244631d1036..0000000000000000000000000000000000000000 --- a/model-00004-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b3da6f76d2ab65eb05dcfaaac06e402a25fec1132d60f489bdcbc9a1efa2afb -size 4376532008 diff --git a/model-00005-of-00136.safetensors b/model-00005-of-00136.safetensors deleted file mode 100644 index 2058377e83d19313e148471c48e23f20f7e110fe..0000000000000000000000000000000000000000 --- a/model-00005-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b5036085fb6129938182e85b7b7d6c3628fe10c6e32b97bfc4249ce5fc0d3d32 -size 4376532008 diff --git a/model-00006-of-00136.safetensors b/model-00006-of-00136.safetensors deleted file mode 100644 index b27548afc9855c429bc20dea8f4eb1a93d114495..0000000000000000000000000000000000000000 --- a/model-00006-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:28284dea3d9aee202feed3a3392f7699de60db23e9b49b47349baa652591d6e3 -size 4376532080 diff --git a/model-00007-of-00136.safetensors b/model-00007-of-00136.safetensors deleted file mode 100644 index 46d233012258f2300f77ed2951a745132f93d487..0000000000000000000000000000000000000000 --- a/model-00007-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:33a70e24b1e9fa3ddf29893b5eecd04efa339dfb0752724b8cd468fe74f1f7c7 -size 4376532136 diff --git a/model-00008-of-00136.safetensors b/model-00008-of-00136.safetensors deleted file mode 100644 index c5a69f270e38fc02394724997e4ff7e8d7301053..0000000000000000000000000000000000000000 --- a/model-00008-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a4d620332481c19db21da1c5fd47ceaaae6e374b3a8759494c4fb4b7609f7a63 -size 4376532136 diff --git a/model-00009-of-00136.safetensors b/model-00009-of-00136.safetensors deleted file mode 100644 index 81778b5c29a5e0f23bc260754159158910da16c5..0000000000000000000000000000000000000000 --- a/model-00009-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d46f99805058104127044e30cf8b4e5793ec9e22cf9acbadafde70831d9dd98d -size 4376532136 diff --git a/model-00010-of-00136.safetensors b/model-00010-of-00136.safetensors deleted file mode 100644 index 2d57de9e00211be0a28de23dc42ad6a5541d8299..0000000000000000000000000000000000000000 --- a/model-00010-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:31101303d87d7aadc15f132ba057de97ad765711b01017f229db1378c2ce70c4 -size 4376532136 diff --git a/model-00011-of-00136.safetensors b/model-00011-of-00136.safetensors deleted file mode 100644 index a2eb6402a46d0d6ef5315f8fe6acdaac9336657b..0000000000000000000000000000000000000000 --- a/model-00011-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:02492b918ae3538c248991154f3347e8763f3531681ccf4da9f45d5e82c91e12 -size 4376532136 diff --git a/model-00012-of-00136.safetensors b/model-00012-of-00136.safetensors deleted file mode 100644 index f1a3f0fec9837472b728dcf98266fcad78a727f7..0000000000000000000000000000000000000000 --- a/model-00012-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:73fb58757c12b762a7c7b80680305bd7849228496a00f91d927bf018d99e34f5 -size 4376532136 diff --git a/model-00013-of-00136.safetensors b/model-00013-of-00136.safetensors deleted file mode 100644 index adf042931341416aadb684d4755b960142def359..0000000000000000000000000000000000000000 --- a/model-00013-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:443450811bea17b1f6697bfd2bf37f56d069c88f0d2c33353da8c63b52aa276d -size 4376532136 diff --git a/model-00014-of-00136.safetensors b/model-00014-of-00136.safetensors deleted file mode 100644 index 333299c37309eeea0e8759b4c1d6eb3b8557925b..0000000000000000000000000000000000000000 --- a/model-00014-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0750dd07a9e10758018f4e895599ee9e97f71fbb72d222564efe0756a89cda6c -size 4376532136 diff --git a/model-00015-of-00136.safetensors b/model-00015-of-00136.safetensors deleted file mode 100644 index 33d1c635d01dd80738c04e9dfe3492afc96dae26..0000000000000000000000000000000000000000 --- a/model-00015-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:19530973fa9ccff9d8e54444f6997b09986223bb18c4e29f253f725a504ddd9f -size 4376532136 diff --git a/model-00016-of-00136.safetensors b/model-00016-of-00136.safetensors deleted file mode 100644 index edcf2ca205bf725b54b6c49d3e3360a149bb249e..0000000000000000000000000000000000000000 --- a/model-00016-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4364ed56e0a4532551e0bf4b304d5e0f4640c701da4eb2440e81ce5d579ab88c -size 4376532136 diff --git a/model-00017-of-00136.safetensors b/model-00017-of-00136.safetensors deleted file mode 100644 index 7de05e41349b0d6240c816f9de41e394caa7a9b1..0000000000000000000000000000000000000000 --- a/model-00017-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b9140e9e3a001e50a3346b287fa3c5857e3734dfbaad0bb1a7bfc7118d17b214 -size 4376532136 diff --git a/model-00018-of-00136.safetensors b/model-00018-of-00136.safetensors deleted file mode 100644 index a35a901bfeda1a8d965ee78a65fa67dfd2ce2d84..0000000000000000000000000000000000000000 --- a/model-00018-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bd28252d2d6b3e1bb5c208b666765f90e5dee44bbdf9ebd111da788cafaa9c17 -size 4376532136 diff --git a/model-00019-of-00136.safetensors b/model-00019-of-00136.safetensors deleted file mode 100644 index cc1ea1ad4915aafe0824ca3a159d8aa429e53313..0000000000000000000000000000000000000000 --- a/model-00019-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:230ed5bf5d5b147d50852ce74b16a14580e71a9eb81153dae72753029d9b900b -size 4376532136 diff --git a/model-00020-of-00136.safetensors b/model-00020-of-00136.safetensors deleted file mode 100644 index dd1af4621c616e21951cff3ab6c060c0353dfcf4..0000000000000000000000000000000000000000 --- a/model-00020-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a9b2f3743abd955b20bf50bbd57837b8a88363abc7def2e589908ebc14a09db4 -size 4376532136 diff --git a/model-00021-of-00136.safetensors b/model-00021-of-00136.safetensors deleted file mode 100644 index 7d11aca32a7c479ee7206a39786a007a47abbd0b..0000000000000000000000000000000000000000 --- a/model-00021-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d8137c48fc14479ded5710e35bb0cd360bde442b03865c61a6487436f5ef4c0a -size 4376532136 diff --git a/model-00022-of-00136.safetensors b/model-00022-of-00136.safetensors deleted file mode 100644 index 78f57509798c45a377e306bf88cfe0bfea49ce60..0000000000000000000000000000000000000000 --- a/model-00022-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a2c1fb89204f6d0f716900f046379d4c7483fd0f98e848b8d0471872e6dbbd7c -size 4376532136 diff --git a/model-00023-of-00136.safetensors b/model-00023-of-00136.safetensors deleted file mode 100644 index 0a31c6313eb5381e43091e282e4b3f84012520a5..0000000000000000000000000000000000000000 --- a/model-00023-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5bf178a4ae6720fff982f7ac92f757532364f4b43492fd08e64832f9605b179e -size 4376532136 diff --git a/model-00024-of-00136.safetensors b/model-00024-of-00136.safetensors deleted file mode 100644 index 16689251d62d083729b6fd4e67af7c190a32e236..0000000000000000000000000000000000000000 --- a/model-00024-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6ab70fea330dc47a2fea057dab3aebed5127b067f10f3e51bbf8f2f8f91e1a03 -size 4376532136 diff --git a/model-00025-of-00136.safetensors b/model-00025-of-00136.safetensors deleted file mode 100644 index 45aaa56d751acf120046651a69399e39ab6e8272..0000000000000000000000000000000000000000 --- a/model-00025-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:066fed1d407581399754e2d1a42abdee73a807c760af8f4b5c0ad06d4b52da15 -size 4376532136 diff --git a/model-00026-of-00136.safetensors b/model-00026-of-00136.safetensors deleted file mode 100644 index 2c5147df4c29f517347030af1b9f9e1415d59838..0000000000000000000000000000000000000000 --- a/model-00026-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7ea778b8318f4923d27c110f7dfaffe3975d5d054bdea1561ec025d3f37232a9 -size 4376532136 diff --git a/model-00027-of-00136.safetensors b/model-00027-of-00136.safetensors deleted file mode 100644 index 95f8f481874a48c27f2ff98ec5032462c658abf5..0000000000000000000000000000000000000000 --- a/model-00027-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6eac84b1e66897282b8f6b2a611655669bf5ba260f665ec5a5ec4ce2ee3e9827 -size 4376532136 diff --git a/model-00028-of-00136.safetensors b/model-00028-of-00136.safetensors deleted file mode 100644 index 0b6d076a4887c32abea7e6a92adc43a48265e73a..0000000000000000000000000000000000000000 --- a/model-00028-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:28c7f50b95d8d0342b91d85736d755e2e0ecdf6078e21b36e5686482cfb54f7e -size 4376532136 diff --git a/model-00029-of-00136.safetensors b/model-00029-of-00136.safetensors deleted file mode 100644 index 2ce72cb9156085152d4f769c269455b23a9c19e7..0000000000000000000000000000000000000000 --- a/model-00029-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d77df85a104ace107c8c7af5e10481751efbc272e9ddeb7d2504a47c5ca702a4 -size 4376532136 diff --git a/model-00030-of-00136.safetensors b/model-00030-of-00136.safetensors deleted file mode 100644 index 14ed3f64412fce6b09a1e78c110ba97ec939aee0..0000000000000000000000000000000000000000 --- a/model-00030-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3435b00b747f3f15d703b3fdc1f1fc1076116259ef25d73f3f89965eb03d6c32 -size 4376532136 diff --git a/model-00031-of-00136.safetensors b/model-00031-of-00136.safetensors deleted file mode 100644 index 0162943eff226a970ba6b4f63d67952bbd5d71c1..0000000000000000000000000000000000000000 --- a/model-00031-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d51be03cd112238f6a175cb4884a991c9d1380aaaf429a64a35389ff5cf83290 -size 4376532136 diff --git a/model-00032-of-00136.safetensors b/model-00032-of-00136.safetensors deleted file mode 100644 index 4873be60564f2056a6e5aaa97f1cbed6dbdc2cce..0000000000000000000000000000000000000000 --- a/model-00032-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f134bb0ba8c67a8cbd6f39bba910abbf98a5794d08afe6d5c2992245727c5fce -size 4376532136 diff --git a/model-00033-of-00136.safetensors b/model-00033-of-00136.safetensors deleted file mode 100644 index 1c9c4593054e8085cb3ad2ffe74a408aabd62aaa..0000000000000000000000000000000000000000 --- a/model-00033-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:eea738b166db0baf4cd832ebfddbe3df0cb9ca502f0dbeb9ada7eaf5acdeb42c -size 4376532136 diff --git a/model-00034-of-00136.safetensors b/model-00034-of-00136.safetensors deleted file mode 100644 index 3390d82fe2293e75a88f776ad5131026e82c3891..0000000000000000000000000000000000000000 --- a/model-00034-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d116c5def59f6ef9b70f822a48ad2448e74558e84059117ec4c522c1465cb897 -size 4376532136 diff --git a/model-00035-of-00136.safetensors b/model-00035-of-00136.safetensors deleted file mode 100644 index 449bc77e10d1ed5ed8f3083478e72a7b8daafcff..0000000000000000000000000000000000000000 --- a/model-00035-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:70a09ea68425b478e647aa569c5dfeb6d03326ae596289397bf2bee15401f651 -size 4376532136 diff --git a/model-00036-of-00136.safetensors b/model-00036-of-00136.safetensors deleted file mode 100644 index 1a13feb9f850c0404ff53b10d69e80e2ad357812..0000000000000000000000000000000000000000 --- a/model-00036-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5b70a8b0a14b29d003bf946f97738fe1b34c527c791005789cddf9b6d8c32b52 -size 4376532136 diff --git a/model-00037-of-00136.safetensors b/model-00037-of-00136.safetensors deleted file mode 100644 index 5db8271cc5a0b61f1f950ebb0776fe9f36a41a31..0000000000000000000000000000000000000000 --- a/model-00037-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a494a26d9b8f29e93d1b67d5df7cbad43107234c27067c93ae44c671147fae10 -size 4376532136 diff --git a/model-00038-of-00136.safetensors b/model-00038-of-00136.safetensors deleted file mode 100644 index bd98e6df2c6c9e5a89d8ec448557b566960e65bb..0000000000000000000000000000000000000000 --- a/model-00038-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:32d873bf8686554e7b30f62e70b2f5198185e8573c3102c340b3c344d1f0e205 -size 4376532136 diff --git a/model-00039-of-00136.safetensors b/model-00039-of-00136.safetensors deleted file mode 100644 index 7108a533220a2ab675422d27d6532ff302ab2e2a..0000000000000000000000000000000000000000 --- a/model-00039-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2608d98681a4c70c978677b8f2fba33d5d80e6892c6c10f8ccca1edbf3cd9b05 -size 4376532136 diff --git a/model-00040-of-00136.safetensors b/model-00040-of-00136.safetensors deleted file mode 100644 index 786cd1e9fc5e626f98e2a43f288d00c778dfaf07..0000000000000000000000000000000000000000 --- a/model-00040-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fc82db6958c9ce83c2b8203fb8814dd5d3a4c4a2166ea303311bd0ac2a6cdd99 -size 4376532136 diff --git a/model-00041-of-00136.safetensors b/model-00041-of-00136.safetensors deleted file mode 100644 index 43f92342c5da0a7e3b6131290b599f3659e32488..0000000000000000000000000000000000000000 --- a/model-00041-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7ad833ce919c65186b3086c91b706ab9b5e3e5fd1fe47acdabed5a1a203a489a -size 4376532136 diff --git a/model-00042-of-00136.safetensors b/model-00042-of-00136.safetensors deleted file mode 100644 index 66ccebae96710aab2e4bf3cb495185e88cbcd900..0000000000000000000000000000000000000000 --- a/model-00042-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:726d9a6984aad311668e5d5f3667ff9228007e486ee9fecc770e84feafbaae2e -size 4376532136 diff --git a/model-00043-of-00136.safetensors b/model-00043-of-00136.safetensors deleted file mode 100644 index 1006f13fb61afdd40d63eb3220f8e55cf8cbea98..0000000000000000000000000000000000000000 --- a/model-00043-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7873a5c81148565a7b0607d605f64b49a8c7c383590365f5fa00e604f99f8de1 -size 4376532136 diff --git a/model-00044-of-00136.safetensors b/model-00044-of-00136.safetensors deleted file mode 100644 index 768fcf72f5e45b9ef2c10a33a1c1b7ffae3e3af4..0000000000000000000000000000000000000000 --- a/model-00044-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5f1f6e632629600b0d6a49dc1b2ad0bb7c01ce449b6a4a32adbb725096d64638 -size 4376532136 diff --git a/model-00045-of-00136.safetensors b/model-00045-of-00136.safetensors deleted file mode 100644 index c79105e704a45d3a9c359ada9a87b5d4c98120a8..0000000000000000000000000000000000000000 --- a/model-00045-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:adb4436b4f581a6dfad93c26d636bf1699d22ced29e2cd03c757145101df2723 -size 4946277840 diff --git a/model-00046-of-00136.safetensors b/model-00046-of-00136.safetensors deleted file mode 100644 index 5809691aa0ffc8095118cfe9015303e568831b26..0000000000000000000000000000000000000000 --- a/model-00046-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:65f4583a6ad45d8bd8b65841199da6eb89591f2435f43a5de810bbfc917109a6 -size 4368249064 diff --git a/model-00047-of-00136.safetensors b/model-00047-of-00136.safetensors deleted file mode 100644 index 676c32b335a39d49f110a3c98caeff99f0600691..0000000000000000000000000000000000000000 --- a/model-00047-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b29344bb2f8f342f104668a4066229a15f4ae13427b15bcac48bf3bdacddeefb -size 4227874384 diff --git a/model-00048-of-00136.safetensors b/model-00048-of-00136.safetensors deleted file mode 100644 index 0b7b90df01ac477ea13b4e3f74ec24d49e0bae6b..0000000000000000000000000000000000000000 --- a/model-00048-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1d7e9a9279fa56f3eda2d9eb07de37d471909866edbf906381a8c34e048f809c -size 4227874384 diff --git a/model-00049-of-00136.safetensors b/model-00049-of-00136.safetensors deleted file mode 100644 index b1c11e1e37e322446baa8f3b662525f600b24eca..0000000000000000000000000000000000000000 --- a/model-00049-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:befa0de4ba68e8b9dcdf6d9f09f2ffb6d5f79b1cfe5129f34c05a23cd9e016d4 -size 4227874384 diff --git a/model-00050-of-00136.safetensors b/model-00050-of-00136.safetensors deleted file mode 100644 index 12a9aaf91e1fc685c8755ebc07012edee9de9bd1..0000000000000000000000000000000000000000 --- a/model-00050-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9b93979ebbcf367f58410ea345ebd3a86aa4c2bfd4febfcfcf19b6f411a24279 -size 4227874384 diff --git a/model-00051-of-00136.safetensors b/model-00051-of-00136.safetensors deleted file mode 100644 index 93a0cf91b888f7115dd64c1d61b178956846c023..0000000000000000000000000000000000000000 --- a/model-00051-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:77c1e4e9c11af1cab3296b4b8a4f16d0d9acf0e9eeb2dad12a48a1e2f5cb6d56 -size 4227874448 diff --git a/model-00052-of-00136.safetensors b/model-00052-of-00136.safetensors deleted file mode 100644 index 1c0f99a8a91682b28ddd6e6b30d3fe836d7cf3d1..0000000000000000000000000000000000000000 --- a/model-00052-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:575339c711e522493a3e57b7fcca683e658427bdc3d3afd9fda8a44d72eeff24 -size 4227874512 diff --git a/model-00053-of-00136.safetensors b/model-00053-of-00136.safetensors deleted file mode 100644 index 8664073676516bc2a12af5eb2837cc4c86bc6d61..0000000000000000000000000000000000000000 --- a/model-00053-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7e6df063edef51e1b5c21f9551bad999e82c52cd442188d743de999615bdf711 -size 4227874512 diff --git a/model-00054-of-00136.safetensors b/model-00054-of-00136.safetensors deleted file mode 100644 index 20bbb3d431930592a55f57cdb1bf8c7011d483e5..0000000000000000000000000000000000000000 --- a/model-00054-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0fadeb1267b724cc5050cc25af23f6d7eb905e84029161c32bb52c8094cd28f2 -size 4227874512 diff --git a/model-00055-of-00136.safetensors b/model-00055-of-00136.safetensors deleted file mode 100644 index 970639df8adf9b7c0af8a4e5787de23eb4d2b6d9..0000000000000000000000000000000000000000 --- a/model-00055-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:152fe8dc7cdd37cb76022a18b9b68126faf2e56b238ca5029dd073befdcff370 -size 4227874512 diff --git a/model-00056-of-00136.safetensors b/model-00056-of-00136.safetensors deleted file mode 100644 index 135176f04359c9651a1ba40cb9201338bdc1942c..0000000000000000000000000000000000000000 --- a/model-00056-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8b7522025e9780951a42e2de939221a8fef02a813d33906e6b3ad0784cc34a03 -size 4227874512 diff --git a/model-00057-of-00136.safetensors b/model-00057-of-00136.safetensors deleted file mode 100644 index 4cc99a581c865437209ba5f3e303ecdfbe312e94..0000000000000000000000000000000000000000 --- a/model-00057-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7afc40248d80fabf82d61b3a9fdff7389784d346e4eace1efc0f39afec698aee -size 4227874512 diff --git a/model-00058-of-00136.safetensors b/model-00058-of-00136.safetensors deleted file mode 100644 index b4e03bfbb29dc70fe6766b3579d4193b1763bf9b..0000000000000000000000000000000000000000 --- a/model-00058-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ae8aa545f80424adfe0664bd560594296e8ae6cbd2c7f1b15307db387f6954ea -size 4227874512 diff --git a/model-00059-of-00136.safetensors b/model-00059-of-00136.safetensors deleted file mode 100644 index 7c125eee8c7f246408b1b56fec44f906fcabc551..0000000000000000000000000000000000000000 --- a/model-00059-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:45f92dc4bb269a2bba1fa2e26129224cdf2c20fa0521d21f9691041e3efee4f5 -size 4227874512 diff --git a/model-00060-of-00136.safetensors b/model-00060-of-00136.safetensors deleted file mode 100644 index 1f0a2853d4defeb91e5182da637484b9c456744d..0000000000000000000000000000000000000000 --- a/model-00060-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9215332ee57433d88a23aa765f75118f654712af067360612031b05a7be621b4 -size 4227874512 diff --git a/model-00061-of-00136.safetensors b/model-00061-of-00136.safetensors deleted file mode 100644 index 77ac8d5c76f809b3491794bb647f53e49603ae3e..0000000000000000000000000000000000000000 --- a/model-00061-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b5cd67b0b7a9027f31589fafc221edfa490218b74cabd2ede5b0387fd82d4e8 -size 4227874512 diff --git a/model-00062-of-00136.safetensors b/model-00062-of-00136.safetensors deleted file mode 100644 index f057bd8fce3fc89b729230570a824003c6f2e1d2..0000000000000000000000000000000000000000 --- a/model-00062-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d023e32d74f017ebac0175fee9d7b5b2515d808878fec350b9ff9f7f435f72da -size 4227874512 diff --git a/model-00063-of-00136.safetensors b/model-00063-of-00136.safetensors deleted file mode 100644 index e510de6fc814dda9c5a156e070198f43d09c12a6..0000000000000000000000000000000000000000 --- a/model-00063-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ccf60de68df3c9949644eae240d8f15cb4fec51c74f45cbec2735e7d4eff694b -size 4227874512 diff --git a/model-00064-of-00136.safetensors b/model-00064-of-00136.safetensors deleted file mode 100644 index 2ba8c528691b3e978134f6205b51e9a101fe5004..0000000000000000000000000000000000000000 --- a/model-00064-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:51b88121956bd3f67ded9957b1785ee978f6efb8fc998c13fa8b16a9d20c9e84 -size 4227874512 diff --git a/model-00065-of-00136.safetensors b/model-00065-of-00136.safetensors deleted file mode 100644 index e1f094ea53656d52e51152985bfeaadf3ccb746f..0000000000000000000000000000000000000000 --- a/model-00065-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9a29e170c79f6213d9a74ee9a92132862dd6b9a9d76808ce28d34e268f607643 -size 4227874512 diff --git a/model-00066-of-00136.safetensors b/model-00066-of-00136.safetensors deleted file mode 100644 index 33d4be0bdf961e29cc275d99b08eb18ebf8899bb..0000000000000000000000000000000000000000 --- a/model-00066-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f159b14f24cffac1918648b448999d5889a67be5bd6f4a814c4127bce1483a06 -size 4227874512 diff --git a/model-00067-of-00136.safetensors b/model-00067-of-00136.safetensors deleted file mode 100644 index 1d75ab1eb10c6ee66067c7ff5679407a77f51812..0000000000000000000000000000000000000000 --- a/model-00067-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b7e65db562104867b1910ad3a97f7a7057a42786444e9f45e31c1f9cc441ce89 -size 4227874512 diff --git a/model-00068-of-00136.safetensors b/model-00068-of-00136.safetensors deleted file mode 100644 index 7ea3fbcc7bdb6b1f938a80444f2b9c9570c7cd1a..0000000000000000000000000000000000000000 --- a/model-00068-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:11ef03a67703ae1cbfb84029b13cd1e9301b6a544518cfc7ae73c66b0b82ab6e -size 4227874512 diff --git a/model-00069-of-00136.safetensors b/model-00069-of-00136.safetensors deleted file mode 100644 index 53d423d9d7c8913d917611f505fd6950b03cb5fd..0000000000000000000000000000000000000000 --- a/model-00069-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8cfc1f427f770dd68fac1e75061cc03492cd14d69479345ada4e94045201bb3b -size 4227874512 diff --git a/model-00070-of-00136.safetensors b/model-00070-of-00136.safetensors deleted file mode 100644 index ec492a19132b8a2e85e68c50bce4c6017d270f46..0000000000000000000000000000000000000000 --- a/model-00070-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7d8de5b3f88cc8d1e1ded6fbd5e745ea59f978c7da49a0ccf51dff534e0b504b -size 4227874512 diff --git a/model-00071-of-00136.safetensors b/model-00071-of-00136.safetensors deleted file mode 100644 index 8ca1ecdb485d889145dad04df3ccce678f4ba0a3..0000000000000000000000000000000000000000 --- a/model-00071-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a455501229fac46752fb46948629f03a2470f832ff094ddabc1122a618fd668a -size 4227874512 diff --git a/model-00072-of-00136.safetensors b/model-00072-of-00136.safetensors deleted file mode 100644 index fa760c37590e02743275c406b4b7a2fad211495c..0000000000000000000000000000000000000000 --- a/model-00072-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:59e5bfcabb5436b6397ae24386af74863e28817188d8d2b0dc6d732a62d8ce30 -size 4227874512 diff --git a/model-00073-of-00136.safetensors b/model-00073-of-00136.safetensors deleted file mode 100644 index 285ff56306162d4fca769fd414620b4001ac4337..0000000000000000000000000000000000000000 --- a/model-00073-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e7465a77bb309b7c9d777ab1e8ea5f6449e240162ec42167a300a7e90656cacd -size 4227874512 diff --git a/model-00074-of-00136.safetensors b/model-00074-of-00136.safetensors deleted file mode 100644 index bca249a4213347ddd88e9c0ca4da7039c06ee04e..0000000000000000000000000000000000000000 --- a/model-00074-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:43d9125194166d82fbdbcaff1015b8abf2d6ef0ccca2f88971f8b93b8a1d1d55 -size 4227874512 diff --git a/model-00075-of-00136.safetensors b/model-00075-of-00136.safetensors deleted file mode 100644 index 0d7bbe40d2c0f668e5150c016b465957d146b91a..0000000000000000000000000000000000000000 --- a/model-00075-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5441a4bdcbc311dd9ac6d8ecf4f72480e0a7c090c67d79624fb2ac153ec05778 -size 4227874512 diff --git a/model-00076-of-00136.safetensors b/model-00076-of-00136.safetensors deleted file mode 100644 index b430f0c43d44d48d1999848796da3d6c2192ac29..0000000000000000000000000000000000000000 --- a/model-00076-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5fa71b8b5db28273c1884bbc5e839e30a950d23e48bd1a8c91d36eb297e0556b -size 4227874512 diff --git a/model-00077-of-00136.safetensors b/model-00077-of-00136.safetensors deleted file mode 100644 index 62c7331969cb1b2c2b4b9e9334b2c38f3d9fe0e1..0000000000000000000000000000000000000000 --- a/model-00077-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4bbde8da7ef160db243fd023891311f82c951e34b960d9ac71c591daec85e153 -size 4227874512 diff --git a/model-00078-of-00136.safetensors b/model-00078-of-00136.safetensors deleted file mode 100644 index af3e538faceaa1131a5a7e060090207e6a79502c..0000000000000000000000000000000000000000 --- a/model-00078-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fe62097271cca2e9188ad5d4193415322a1167a42681a3bcf08e2efecb6e2296 -size 4227874512 diff --git a/model-00079-of-00136.safetensors b/model-00079-of-00136.safetensors deleted file mode 100644 index edd4ffc515e63059dbf49d5c2e70ae21dbbd761a..0000000000000000000000000000000000000000 --- a/model-00079-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d01102048595d4292f0638d776f4e150ac553c0410fe66943de5b4f7d427892b -size 4227874512 diff --git a/model-00080-of-00136.safetensors b/model-00080-of-00136.safetensors deleted file mode 100644 index 7d4a44934aae8463b5bc75f3098b27fcb7171365..0000000000000000000000000000000000000000 --- a/model-00080-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:57c5c740da4f30ed6928b633a020b9e54c5be98e86f5e5b56c126a1fe9df7c8f -size 4227874512 diff --git a/model-00081-of-00136.safetensors b/model-00081-of-00136.safetensors deleted file mode 100644 index 667478fcafb1f69c5322f8ae65e8c36e48db220f..0000000000000000000000000000000000000000 --- a/model-00081-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f2e3a140bf74db22e9d05136bdfb59cee99e12135198cd32f68cf2540ebc70ef -size 4227874512 diff --git a/model-00082-of-00136.safetensors b/model-00082-of-00136.safetensors deleted file mode 100644 index f794309a3b7b8b6e2d835af0732d4f9878ca9137..0000000000000000000000000000000000000000 --- a/model-00082-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:297fe95c4766dd149a7072fa1b6d6dab0f9e90f44e4d6e5486bf8a628feb43ef -size 4227874512 diff --git a/model-00083-of-00136.safetensors b/model-00083-of-00136.safetensors deleted file mode 100644 index 0785e09196db129beeed59abe7dc2e20c9a39d47..0000000000000000000000000000000000000000 --- a/model-00083-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:83d70ab4a9135f4c3762e613431640871cc5c41c757e8b8bd6e5ac6360fbc330 -size 4227874512 diff --git a/model-00084-of-00136.safetensors b/model-00084-of-00136.safetensors deleted file mode 100644 index ecec5dfac0af7cfa36fd313b982a8053c2422d6e..0000000000000000000000000000000000000000 --- a/model-00084-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5030bd32ef977166530ebaf004ff28da803f77e6c96bfff01d0850623e0e8ced -size 4227874512 diff --git a/model-00085-of-00136.safetensors b/model-00085-of-00136.safetensors deleted file mode 100644 index 254a88a043b5e6c347614bc4cef9d391a2014e10..0000000000000000000000000000000000000000 --- a/model-00085-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:368198dc1236a731092e6cdd5fe8ddd28144070ae1f49ab061140e2ffebaa8c7 -size 4227874512 diff --git a/model-00086-of-00136.safetensors b/model-00086-of-00136.safetensors deleted file mode 100644 index b737abe5cbfd3ad641db76578d01592bb86ba313..0000000000000000000000000000000000000000 --- a/model-00086-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fd9651d5e1df2c6066ad42e137f4d4cd7816b1103fe72dc677e616b9750f3c66 -size 4227874512 diff --git a/model-00087-of-00136.safetensors b/model-00087-of-00136.safetensors deleted file mode 100644 index 060602c0d2b72454c5117c01cbde27015e806792..0000000000000000000000000000000000000000 --- a/model-00087-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5a753300315dd9e9a295f5efe9d90bef02ddf3a63ae4187e9ab9449e9460dad0 -size 4227874512 diff --git a/model-00088-of-00136.safetensors b/model-00088-of-00136.safetensors deleted file mode 100644 index cf3b3878f57a24138b4f5789ab21536f3f20e84e..0000000000000000000000000000000000000000 --- a/model-00088-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:83e0cd97329cc047152dcb00d1920cd3f7fd1591976b23ce0062a3317bb7bacc -size 4227874512 diff --git a/model-00089-of-00136.safetensors b/model-00089-of-00136.safetensors deleted file mode 100644 index 4d2f2612a10bb26db8e1082bb7dd80618e3353f6..0000000000000000000000000000000000000000 --- a/model-00089-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f18062cab0e50714311a9d5c6b3e0794f753d15549235ab08da3b94e01fd1747 -size 4227874512 diff --git a/model-00090-of-00136.safetensors b/model-00090-of-00136.safetensors deleted file mode 100644 index d619749589b33abc8b97c3fdd91b271e093a5d9b..0000000000000000000000000000000000000000 --- a/model-00090-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8ed90cf92f92acd67bad8044a483875d79ad54f31ce3f2b4835a152e132f0a24 -size 4988542792 diff --git a/model-00091-of-00136.safetensors b/model-00091-of-00136.safetensors deleted file mode 100644 index 07f85deffc229de7f34f379cf34f9203c1fc46eb..0000000000000000000000000000000000000000 --- a/model-00091-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:018c16c807dce82583d60ce30e9f6b8b3be0f49b791577fbd64d8c9118ab9295 -size 3567269104 diff --git a/model-00092-of-00136.safetensors b/model-00092-of-00136.safetensors deleted file mode 100644 index e9a268d379c0c3885870a1905053ac683924c494..0000000000000000000000000000000000000000 --- a/model-00092-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a1b0bf535d6ecacd1c6d26720dd69bb6f0c3680320b693196d703c633e85091f -size 4227874128 diff --git a/model-00093-of-00136.safetensors b/model-00093-of-00136.safetensors deleted file mode 100644 index 6b7ed4e10ca36d8b932d0330b933e4787d28fb60..0000000000000000000000000000000000000000 --- a/model-00093-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8e35feaf00c70510b01d4064f0c9b269a5382f664a216323ecc51aee02398fa5 -size 4227874128 diff --git a/model-00094-of-00136.safetensors b/model-00094-of-00136.safetensors deleted file mode 100644 index 954d6b526050b601f6b0da2f7431d0f1c4b8c5b6..0000000000000000000000000000000000000000 --- a/model-00094-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:979680180cc96ac42385837bb95f3c266790348844a5a60818276568325f41da -size 4227874128 diff --git a/model-00095-of-00136.safetensors b/model-00095-of-00136.safetensors deleted file mode 100644 index c7fd527c5eb5ef06e2865fc1ae7d77fbcd472c60..0000000000000000000000000000000000000000 --- a/model-00095-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f6627ed86759e9899fe80980d14660d55fe3f55de7f1e2830586bea967801546 -size 4227874128 diff --git a/model-00096-of-00136.safetensors b/model-00096-of-00136.safetensors deleted file mode 100644 index 798511f268ab5ee42a68f9d88fca738bec4f2c1d..0000000000000000000000000000000000000000 --- a/model-00096-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1e9e7526aed0831050209db516a2abd9c9828380bdde8e595b8e880ee7fb33c0 -size 4227874192 diff --git a/model-00097-of-00136.safetensors b/model-00097-of-00136.safetensors deleted file mode 100644 index 3c0e37113c03829f8fea410eccdb961b0c697eaf..0000000000000000000000000000000000000000 --- a/model-00097-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fe64452c066738fc5c5bca519055b42eff706f4d59527611e926dc87e98f9ef0 -size 4227874256 diff --git a/model-00098-of-00136.safetensors b/model-00098-of-00136.safetensors deleted file mode 100644 index 055dfecbd2f234384d548145e2589b045fbfdac1..0000000000000000000000000000000000000000 --- a/model-00098-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4812a933f44a4f04c525a1b98d8e9af7b55332eb0ee5414ff2f2bbadf9bedf45 -size 4227874256 diff --git a/model-00099-of-00136.safetensors b/model-00099-of-00136.safetensors deleted file mode 100644 index 322d64c1788c0d6d44dd77fae3e5c60027c78503..0000000000000000000000000000000000000000 --- a/model-00099-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:296211578f1d1bc20370b24f799ee6e7e7f05395b49b0d2182287fd3c100c942 -size 4227874256 diff --git a/model-00100-of-00136.safetensors b/model-00100-of-00136.safetensors deleted file mode 100644 index c7f3bea5d04fc4f1a8deaa408fd4a537368a1741..0000000000000000000000000000000000000000 --- a/model-00100-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2e4c97cc097e098054fd7417291bcffeb67f881268528b3ad4b571d45ce773b8 -size 4227874256 diff --git a/model-00101-of-00136.safetensors b/model-00101-of-00136.safetensors deleted file mode 100644 index c665cc8ed3c5dffdca4976d160d36498f20f7cbf..0000000000000000000000000000000000000000 --- a/model-00101-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3c30a43bf1a0df4b7d7819b43c49246079bcdec60c682d9088cfc3bd011e1dcb -size 4227874256 diff --git a/model-00102-of-00136.safetensors b/model-00102-of-00136.safetensors deleted file mode 100644 index 349551546444d05e593a10c3b456b8fdfe407161..0000000000000000000000000000000000000000 --- a/model-00102-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:373a85e127bc3a67bb82bf6637812a0488b6ac90cdaa49fef2cb2c2f36390e78 -size 4227874256 diff --git a/model-00103-of-00136.safetensors b/model-00103-of-00136.safetensors deleted file mode 100644 index 088fe0f59702eac22156009b0c2c49b13a2633b6..0000000000000000000000000000000000000000 --- a/model-00103-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0785cad32ebce10c17517ef9c4e5765062a8c78f5793f3d076bb98f323fb1ac2 -size 4227874256 diff --git a/model-00104-of-00136.safetensors b/model-00104-of-00136.safetensors deleted file mode 100644 index de78fe5bbbfce70a7311e410d32c7809fd3a1a7e..0000000000000000000000000000000000000000 --- a/model-00104-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cb41b65f637a43e24d2b404208dfca6551ff610e281591811bcf3de9948b33ae -size 4227874256 diff --git a/model-00105-of-00136.safetensors b/model-00105-of-00136.safetensors deleted file mode 100644 index d82e0db8b24d9c9ad518d1dc0d085733837b28b1..0000000000000000000000000000000000000000 --- a/model-00105-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a98c4baa83f0ad088d36f7246c93996796c1dcb5608e285627b244cefbf30b3f -size 4227874256 diff --git a/model-00106-of-00136.safetensors b/model-00106-of-00136.safetensors deleted file mode 100644 index 01f0ad3fbcb3db398deb9b15d6bd3512590b8dce..0000000000000000000000000000000000000000 --- a/model-00106-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:70b80e4f8c16480c0191b58e78157cb8ea3f7830e6431d543403442efe84656f -size 4227874256 diff --git a/model-00107-of-00136.safetensors b/model-00107-of-00136.safetensors deleted file mode 100644 index 4d22815cc7ec068106b221553de27783ba49cafc..0000000000000000000000000000000000000000 --- a/model-00107-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4c038b862810fc2dd930bed1f13bfc70842a75f8ec0d672062e711897e062241 -size 4227874256 diff --git a/model-00108-of-00136.safetensors b/model-00108-of-00136.safetensors deleted file mode 100644 index 0c27ab3d7ebbfbe6b3b0b021446e519d61d7b4e1..0000000000000000000000000000000000000000 --- a/model-00108-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b44c497893e4cce0b575aa6ffbddd7329c61f8b6d4e0f7b2b9063d09b06578e0 -size 4227874256 diff --git a/model-00109-of-00136.safetensors b/model-00109-of-00136.safetensors deleted file mode 100644 index e1e2114e7be792b52f4d0d921d484b06de9e853e..0000000000000000000000000000000000000000 --- a/model-00109-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:36f02904484d37af0806ce503c5c0012ff1828e0d4ed97df814dfabe7528b0e8 -size 4227874256 diff --git a/model-00110-of-00136.safetensors b/model-00110-of-00136.safetensors deleted file mode 100644 index 6858260765072509bc3af9e6b4ddc21190bb3d47..0000000000000000000000000000000000000000 --- a/model-00110-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:66e0f89455ffd883a5f49292e577386a2c35137abec0a162e9c89d7ccf3bb462 -size 4227874256 diff --git a/model-00111-of-00136.safetensors b/model-00111-of-00136.safetensors deleted file mode 100644 index 3806833d129035680b4a610531a6336e5be68eb9..0000000000000000000000000000000000000000 --- a/model-00111-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ccb5e3c349cafd10c6db7c1cd2cd866e9301561d2f2251add1dcd3ee8f164b56 -size 4227874256 diff --git a/model-00112-of-00136.safetensors b/model-00112-of-00136.safetensors deleted file mode 100644 index 8f6a32a972d1a75a685e5d4844042d557c35fe82..0000000000000000000000000000000000000000 --- a/model-00112-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fc4e71ff703551eae3c71ca6d5da81696511aecf45d0762ce07ccb46a914db3e -size 4227874256 diff --git a/model-00113-of-00136.safetensors b/model-00113-of-00136.safetensors deleted file mode 100644 index 9fc2cb32e08be0177507557ee4c0bafbc02e228f..0000000000000000000000000000000000000000 --- a/model-00113-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5c589d4aacb1679bf6211f84bae479bc80d5fee97deab783b1c1162617a59e9b -size 4227874256 diff --git a/model-00114-of-00136.safetensors b/model-00114-of-00136.safetensors deleted file mode 100644 index 881c4131a5385a68fd931d9e7c2331654475494a..0000000000000000000000000000000000000000 --- a/model-00114-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ffeb3b9786d851135c93a39df2384febc453647afef4a315aa5e5566b5459873 -size 4227874256 diff --git a/model-00115-of-00136.safetensors b/model-00115-of-00136.safetensors deleted file mode 100644 index 8960efa97155e33197b499caeadcaa8db9cb82f3..0000000000000000000000000000000000000000 --- a/model-00115-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:688f7fe2381a9df5decb4daeb7c33c76ac4a267c37020873663dce4d0499b896 -size 4227874256 diff --git a/model-00116-of-00136.safetensors b/model-00116-of-00136.safetensors deleted file mode 100644 index cf2f1d33a41db09197b5ce00d01cd603510b1970..0000000000000000000000000000000000000000 --- a/model-00116-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:67860ee181cf75b9cc8e8de63b5f130b2b5cce830fe5c50e5b4606fcef1557d9 -size 4227874256 diff --git a/model-00117-of-00136.safetensors b/model-00117-of-00136.safetensors deleted file mode 100644 index eb59bd20d96e2cedc9198ceb2879740c99052265..0000000000000000000000000000000000000000 --- a/model-00117-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f2a1bb95617c82b74c70bd7cd3c45c8c14f9199a71c8534e2dbd894602d829f2 -size 4227874256 diff --git a/model-00118-of-00136.safetensors b/model-00118-of-00136.safetensors deleted file mode 100644 index 1eaa14262c2a1cd7653f7794be462a0ad5ccf407..0000000000000000000000000000000000000000 --- a/model-00118-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cd53e83a99789847054567d8927329a83c938e41a84969d7ada026ad71a3372b -size 4227874256 diff --git a/model-00119-of-00136.safetensors b/model-00119-of-00136.safetensors deleted file mode 100644 index 307f1413e720f34dbfc7f718a22223184ac43367..0000000000000000000000000000000000000000 --- a/model-00119-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f68a1d54b2e6f5a2eeeb58ff8a5cb4ff3140a9019d648b8be4cbd9829543e1c6 -size 4227874256 diff --git a/model-00120-of-00136.safetensors b/model-00120-of-00136.safetensors deleted file mode 100644 index 7bb0d451dffdd579bfc5f5a49e8ba12363e682c0..0000000000000000000000000000000000000000 --- a/model-00120-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:04707cd91e5bae9dcb25eb8b5a216aacf735fd41c66bec3c222f3817ee8d88cf -size 4227874256 diff --git a/model-00121-of-00136.safetensors b/model-00121-of-00136.safetensors deleted file mode 100644 index ce0a9207850e6d0ed132d93a63f38c33d925a122..0000000000000000000000000000000000000000 --- a/model-00121-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e92865c335dee781004f5c125729e2ac227efe8d3d63a810c401e7c210648862 -size 4227874256 diff --git a/model-00122-of-00136.safetensors b/model-00122-of-00136.safetensors deleted file mode 100644 index db55fe9b68968982491bdf89a9bcc86a1e060de0..0000000000000000000000000000000000000000 --- a/model-00122-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6e283060bc0c00104c48b17c9001854e3b9899d9ac31e6991e99ad45fa62bdfd -size 4227874256 diff --git a/model-00123-of-00136.safetensors b/model-00123-of-00136.safetensors deleted file mode 100644 index 03620ec5bb0ea44bd792335b32b8a1524e04624e..0000000000000000000000000000000000000000 --- a/model-00123-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b5bd32d5195609a3d6237acc4b66bf46b72515aa565ff453d1a76b608963d829 -size 4227874256 diff --git a/model-00124-of-00136.safetensors b/model-00124-of-00136.safetensors deleted file mode 100644 index d0e9bcb3a817d5d00edc5a7a3298e46fbff8955f..0000000000000000000000000000000000000000 --- a/model-00124-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bd36397019b987b85c38b3986983630b487ff5e2c5bc9f1c27e62926c5a07d9b -size 4227874256 diff --git a/model-00125-of-00136.safetensors b/model-00125-of-00136.safetensors deleted file mode 100644 index c5257ee7b0fcd18b83ecb932adbe32398c1b6281..0000000000000000000000000000000000000000 --- a/model-00125-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9f74b475495465c8821942cff4aad341288f3960f65718e3c812414f10eca191 -size 4227874256 diff --git a/model-00126-of-00136.safetensors b/model-00126-of-00136.safetensors deleted file mode 100644 index 5ae265b07a190d7d1dccc88b2c9acd51df70f75b..0000000000000000000000000000000000000000 --- a/model-00126-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3f80b0898554eb6b09967aae58c93e30d26fde8b9a1dc02936f634cfbca5fc27 -size 4227874256 diff --git a/model-00127-of-00136.safetensors b/model-00127-of-00136.safetensors deleted file mode 100644 index a139043482b342a7a10a6c9d0f5aa3e166e42e78..0000000000000000000000000000000000000000 --- a/model-00127-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:78e292e40b27c90d986f35f50c77c24d53b931533f5fe71543bbf2f67988d617 -size 4227874256 diff --git a/model-00128-of-00136.safetensors b/model-00128-of-00136.safetensors deleted file mode 100644 index ccf761aa143c34814ab7359abd5a570a1d6deec0..0000000000000000000000000000000000000000 --- a/model-00128-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:13500398c1ff433bbaf81e6e2edb50f831d27550c29376aa05400285e87027f7 -size 4227874256 diff --git a/model-00129-of-00136.safetensors b/model-00129-of-00136.safetensors deleted file mode 100644 index 78e6ec44588743a30ae474ab0629db0c70caa33c..0000000000000000000000000000000000000000 --- a/model-00129-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fefe2a3d9bdc2436b2b99afc96a4b1e8a34125ca791305599bf7b31ad85a8e7c -size 4227874256 diff --git a/model-00130-of-00136.safetensors b/model-00130-of-00136.safetensors deleted file mode 100644 index 5b36acb1665bcc69b8bdfb7c2ad91a60af321607..0000000000000000000000000000000000000000 --- a/model-00130-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4d5349c47237517e77ece48e0a127130b9ff924be2cf2a17403aea7bbecda5bf -size 4227874256 diff --git a/model-00131-of-00136.safetensors b/model-00131-of-00136.safetensors deleted file mode 100644 index f35aa04904d8c31a861f600d5def480c49064320..0000000000000000000000000000000000000000 --- a/model-00131-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:eaede26095c13fe1394bb05eac8213a966d3e03b01b12ec4e71964fd68d37e6e -size 4227874256 diff --git a/model-00132-of-00136.safetensors b/model-00132-of-00136.safetensors deleted file mode 100644 index 7f48712978d3389d1fb2b0cc95bafb720e70d0c6..0000000000000000000000000000000000000000 --- a/model-00132-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8901f6acbf3a45d89eb4da3145a747149acb5cbb5b553e868eb229178fcfcf28 -size 4227874256 diff --git a/model-00133-of-00136.safetensors b/model-00133-of-00136.safetensors deleted file mode 100644 index 4ac3d90fa330742d38487182fee737d72059b65f..0000000000000000000000000000000000000000 --- a/model-00133-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6ceea18e9c29105eb7f18bb0f5ff170fe05978ad75d4073bae066ac360cb001c -size 4227874256 diff --git a/model-00134-of-00136.safetensors b/model-00134-of-00136.safetensors deleted file mode 100644 index eb256f2582b49d8312aea397331d28d467935104..0000000000000000000000000000000000000000 --- a/model-00134-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4ce23b79b2288d565b73f380df264b566670fc55d65042b53bf0fc705eeec1a3 -size 4227874256 diff --git a/model-00135-of-00136.safetensors b/model-00135-of-00136.safetensors deleted file mode 100644 index 8ad93ccd13071f3bfcf1e928e16702c8f2bde4bb..0000000000000000000000000000000000000000 --- a/model-00135-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c076e6212d31769dd6b0d6b0517d8d35497f730327ba656b59d787331432a552 -size 4987570768 diff --git a/model-00136-of-00136.safetensors b/model-00136-of-00136.safetensors deleted file mode 100644 index c46388cbc6a61d88d4a4835fa43cf5c325b9e200..0000000000000000000000000000000000000000 --- a/model-00136-of-00136.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9540fc68ae64babdcb2f5f7e5b1a6855f3c033f0f6f511c46b42e0a80827f348 -size 2939694344 diff --git a/model.safetensors.index.json b/model.safetensors.index.json deleted file mode 100644 index 85de8afc19168c5ed779b8a3b626af35b73c2df8..0000000000000000000000000000000000000000 --- a/model.safetensors.index.json +++ /dev/null @@ -1,17610 +0,0 @@ -{ - "metadata": { - "total_size": 1162411643904 - }, - "weight_map": { - "model.word_embeddings.weight": "model-00001-of-00136.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00136.safetensors", - "model.layers.0.attention.query_key_value.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.4.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.5.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.6.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.7.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.8.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.9.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.10.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.11.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.12.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.13.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.14.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.15.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.16.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.17.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.18.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.19.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.20.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.21.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.22.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.23.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.24.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.25.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.26.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.27.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.28.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.29.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.30.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.31.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.32.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.33.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.34.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.35.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.36.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.37.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.38.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.39.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.40.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.41.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.42.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.43.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.44.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.45.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.46.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.47.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.48.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.49.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.50.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.51.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.52.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.53.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.54.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.55.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.56.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.57.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.58.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.59.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.60.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.61.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.62.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.0.mlp.experts.63.gate_proj.weight": "model-00001-of-00136.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00136.safetensors", - "model.layers.1.attention.query_key_value.weight": "model-00001-of-00136.safetensors", - "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.input_layernorm.weight": "model-00002-of-00136.safetensors", - "model.layers.2.attention.query_key_value.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00002-of-00136.safetensors", - "model.layers.3.input_layernorm.weight": "model-00002-of-00136.safetensors", - "model.layers.3.attention.query_key_value.weight": "model-00002-of-00136.safetensors", - "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.input_layernorm.weight": "model-00003-of-00136.safetensors", - "model.layers.4.attention.query_key_value.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00003-of-00136.safetensors", - "model.layers.5.input_layernorm.weight": "model-00003-of-00136.safetensors", - "model.layers.5.attention.query_key_value.weight": "model-00003-of-00136.safetensors", - "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.input_layernorm.weight": "model-00004-of-00136.safetensors", - "model.layers.6.attention.query_key_value.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00004-of-00136.safetensors", - "model.layers.7.input_layernorm.weight": "model-00004-of-00136.safetensors", - "model.layers.7.attention.query_key_value.weight": "model-00004-of-00136.safetensors", - "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.input_layernorm.weight": "model-00005-of-00136.safetensors", - "model.layers.8.attention.query_key_value.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00005-of-00136.safetensors", - "model.layers.9.input_layernorm.weight": "model-00005-of-00136.safetensors", - "model.layers.9.attention.query_key_value.weight": "model-00005-of-00136.safetensors", - "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.input_layernorm.weight": "model-00006-of-00136.safetensors", - "model.layers.10.attention.query_key_value.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00006-of-00136.safetensors", - "model.layers.11.input_layernorm.weight": "model-00006-of-00136.safetensors", - "model.layers.11.attention.query_key_value.weight": "model-00006-of-00136.safetensors", - "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.input_layernorm.weight": "model-00007-of-00136.safetensors", - "model.layers.12.attention.query_key_value.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00007-of-00136.safetensors", - "model.layers.13.input_layernorm.weight": "model-00007-of-00136.safetensors", - "model.layers.13.attention.query_key_value.weight": "model-00007-of-00136.safetensors", - "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.input_layernorm.weight": "model-00008-of-00136.safetensors", - "model.layers.14.attention.query_key_value.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00008-of-00136.safetensors", - "model.layers.15.input_layernorm.weight": "model-00008-of-00136.safetensors", - "model.layers.15.attention.query_key_value.weight": "model-00008-of-00136.safetensors", - "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.input_layernorm.weight": "model-00009-of-00136.safetensors", - "model.layers.16.attention.query_key_value.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00009-of-00136.safetensors", - "model.layers.17.input_layernorm.weight": "model-00009-of-00136.safetensors", - "model.layers.17.attention.query_key_value.weight": "model-00009-of-00136.safetensors", - "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.input_layernorm.weight": "model-00010-of-00136.safetensors", - "model.layers.18.attention.query_key_value.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00010-of-00136.safetensors", - "model.layers.19.input_layernorm.weight": "model-00010-of-00136.safetensors", - "model.layers.19.attention.query_key_value.weight": "model-00010-of-00136.safetensors", - "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.input_layernorm.weight": "model-00011-of-00136.safetensors", - "model.layers.20.attention.query_key_value.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00011-of-00136.safetensors", - "model.layers.21.input_layernorm.weight": "model-00011-of-00136.safetensors", - "model.layers.21.attention.query_key_value.weight": "model-00011-of-00136.safetensors", - "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.input_layernorm.weight": "model-00012-of-00136.safetensors", - "model.layers.22.attention.query_key_value.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00012-of-00136.safetensors", - "model.layers.23.input_layernorm.weight": "model-00012-of-00136.safetensors", - "model.layers.23.attention.query_key_value.weight": "model-00012-of-00136.safetensors", - "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.input_layernorm.weight": "model-00013-of-00136.safetensors", - "model.layers.24.attention.query_key_value.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00013-of-00136.safetensors", - "model.layers.25.input_layernorm.weight": "model-00013-of-00136.safetensors", - "model.layers.25.attention.query_key_value.weight": "model-00013-of-00136.safetensors", - "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.input_layernorm.weight": "model-00014-of-00136.safetensors", - "model.layers.26.attention.query_key_value.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00014-of-00136.safetensors", - "model.layers.27.input_layernorm.weight": "model-00014-of-00136.safetensors", - "model.layers.27.attention.query_key_value.weight": "model-00014-of-00136.safetensors", - "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.input_layernorm.weight": "model-00015-of-00136.safetensors", - "model.layers.28.attention.query_key_value.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00015-of-00136.safetensors", - "model.layers.29.input_layernorm.weight": "model-00015-of-00136.safetensors", - "model.layers.29.attention.query_key_value.weight": "model-00015-of-00136.safetensors", - "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.input_layernorm.weight": "model-00016-of-00136.safetensors", - "model.layers.30.attention.query_key_value.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00016-of-00136.safetensors", - "model.layers.31.input_layernorm.weight": "model-00016-of-00136.safetensors", - "model.layers.31.attention.query_key_value.weight": "model-00016-of-00136.safetensors", - "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.input_layernorm.weight": "model-00017-of-00136.safetensors", - "model.layers.32.attention.query_key_value.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00017-of-00136.safetensors", - "model.layers.33.input_layernorm.weight": "model-00017-of-00136.safetensors", - "model.layers.33.attention.query_key_value.weight": "model-00017-of-00136.safetensors", - "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.input_layernorm.weight": "model-00018-of-00136.safetensors", - "model.layers.34.attention.query_key_value.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00018-of-00136.safetensors", - "model.layers.35.input_layernorm.weight": "model-00018-of-00136.safetensors", - "model.layers.35.attention.query_key_value.weight": "model-00018-of-00136.safetensors", - "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.input_layernorm.weight": "model-00019-of-00136.safetensors", - "model.layers.36.attention.query_key_value.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00019-of-00136.safetensors", - "model.layers.37.input_layernorm.weight": "model-00019-of-00136.safetensors", - "model.layers.37.attention.query_key_value.weight": "model-00019-of-00136.safetensors", - "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.input_layernorm.weight": "model-00020-of-00136.safetensors", - "model.layers.38.attention.query_key_value.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00020-of-00136.safetensors", - "model.layers.39.input_layernorm.weight": "model-00020-of-00136.safetensors", - "model.layers.39.attention.query_key_value.weight": "model-00020-of-00136.safetensors", - "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.input_layernorm.weight": "model-00021-of-00136.safetensors", - "model.layers.40.attention.query_key_value.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00021-of-00136.safetensors", - "model.layers.41.input_layernorm.weight": "model-00021-of-00136.safetensors", - "model.layers.41.attention.query_key_value.weight": "model-00021-of-00136.safetensors", - "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.input_layernorm.weight": "model-00022-of-00136.safetensors", - "model.layers.42.attention.query_key_value.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00022-of-00136.safetensors", - "model.layers.43.input_layernorm.weight": "model-00022-of-00136.safetensors", - "model.layers.43.attention.query_key_value.weight": "model-00022-of-00136.safetensors", - "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.input_layernorm.weight": "model-00023-of-00136.safetensors", - "model.layers.44.attention.query_key_value.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00023-of-00136.safetensors", - "model.layers.45.input_layernorm.weight": "model-00023-of-00136.safetensors", - "model.layers.45.attention.query_key_value.weight": "model-00023-of-00136.safetensors", - "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.input_layernorm.weight": "model-00024-of-00136.safetensors", - "model.layers.46.attention.query_key_value.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00024-of-00136.safetensors", - "model.layers.47.input_layernorm.weight": "model-00024-of-00136.safetensors", - "model.layers.47.attention.query_key_value.weight": "model-00024-of-00136.safetensors", - "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.input_layernorm.weight": "model-00025-of-00136.safetensors", - "model.layers.48.attention.query_key_value.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.0.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.1.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.2.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.3.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.4.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.5.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.6.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.7.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.8.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.9.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.10.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.11.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.12.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.13.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.14.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.15.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.16.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.17.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.18.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.19.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.20.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.21.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.22.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.23.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.24.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.25.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.26.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.27.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.28.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.29.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.30.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.31.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.32.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.33.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.34.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.35.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.36.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.37.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.38.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.39.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.40.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.41.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.42.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.43.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.44.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.45.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.46.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.47.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.48.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.49.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.50.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.51.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.52.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.53.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.54.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.55.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.56.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.57.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.58.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.59.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.60.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.61.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.62.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.48.mlp.experts.63.gate_proj.weight": "model-00025-of-00136.safetensors", - "model.layers.49.input_layernorm.weight": "model-00025-of-00136.safetensors", - "model.layers.49.attention.query_key_value.weight": "model-00025-of-00136.safetensors", - "model.layers.49.mlp.experts.0.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.1.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.2.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.3.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.4.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.5.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.6.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.7.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.8.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.9.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.10.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.11.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.12.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.13.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.14.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.15.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.16.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.17.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.18.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.19.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.20.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.21.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.22.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.23.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.24.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.25.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.26.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.27.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.28.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.29.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.30.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.31.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.32.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.33.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.34.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.35.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.36.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.37.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.38.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.39.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.40.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.41.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.42.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.43.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.44.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.45.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.46.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.47.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.48.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.49.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.50.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.51.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.52.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.53.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.54.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.55.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.56.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.57.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.58.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.59.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.60.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.61.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.62.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.49.mlp.experts.63.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.input_layernorm.weight": "model-00026-of-00136.safetensors", - "model.layers.50.attention.query_key_value.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.0.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.1.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.2.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.3.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.4.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.5.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.6.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.7.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.8.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.9.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.10.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.11.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.12.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.13.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.14.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.15.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.16.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.17.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.18.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.19.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.20.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.21.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.22.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.23.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.24.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.25.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.26.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.27.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.28.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.29.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.30.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.31.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.32.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.33.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.34.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.35.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.36.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.37.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.38.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.39.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.40.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.41.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.42.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.43.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.44.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.45.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.46.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.47.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.48.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.49.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.50.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.51.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.52.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.53.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.54.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.55.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.56.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.57.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.58.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.59.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.60.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.61.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.62.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.50.mlp.experts.63.gate_proj.weight": "model-00026-of-00136.safetensors", - "model.layers.51.input_layernorm.weight": "model-00026-of-00136.safetensors", - "model.layers.51.attention.query_key_value.weight": "model-00026-of-00136.safetensors", - "model.layers.51.mlp.experts.0.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.1.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.2.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.3.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.4.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.5.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.6.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.7.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.8.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.9.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.10.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.11.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.12.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.13.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.14.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.15.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.16.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.17.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.18.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.19.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.20.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.21.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.22.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.23.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.24.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.25.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.26.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.27.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.28.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.29.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.30.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.31.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.32.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.33.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.34.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.35.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.36.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.37.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.38.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.39.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.40.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.41.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.42.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.43.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.44.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.45.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.46.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.47.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.48.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.49.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.50.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.51.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.52.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.53.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.54.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.55.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.56.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.57.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.58.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.59.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.60.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.61.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.62.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.51.mlp.experts.63.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.input_layernorm.weight": "model-00027-of-00136.safetensors", - "model.layers.52.attention.query_key_value.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.0.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.1.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.2.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.3.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.4.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.5.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.6.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.7.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.8.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.9.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.10.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.11.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.12.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.13.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.14.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.15.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.16.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.17.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.18.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.19.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.20.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.21.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.22.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.23.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.24.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.25.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.26.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.27.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.28.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.29.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.30.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.31.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.32.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.33.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.34.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.35.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.36.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.37.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.38.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.39.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.40.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.41.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.42.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.43.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.44.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.45.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.46.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.47.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.48.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.49.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.50.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.51.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.52.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.53.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.54.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.55.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.56.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.57.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.58.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.59.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.60.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.61.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.62.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.52.mlp.experts.63.gate_proj.weight": "model-00027-of-00136.safetensors", - "model.layers.53.input_layernorm.weight": "model-00027-of-00136.safetensors", - "model.layers.53.attention.query_key_value.weight": "model-00027-of-00136.safetensors", - "model.layers.53.mlp.experts.0.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.1.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.2.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.3.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.4.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.5.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.6.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.7.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.8.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.9.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.10.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.11.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.12.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.13.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.14.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.15.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.16.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.17.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.18.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.19.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.20.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.21.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.22.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.23.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.24.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.25.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.26.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.27.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.28.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.29.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.30.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.31.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.32.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.33.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.34.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.35.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.36.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.37.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.38.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.39.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.40.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.41.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.42.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.43.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.44.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.45.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.46.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.47.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.48.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.49.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.50.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.51.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.52.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.53.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.54.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.55.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.56.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.57.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.58.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.59.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.60.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.61.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.62.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.53.mlp.experts.63.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.input_layernorm.weight": "model-00028-of-00136.safetensors", - "model.layers.54.attention.query_key_value.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.0.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.1.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.2.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.3.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.4.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.5.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.6.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.7.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.8.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.9.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.10.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.11.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.12.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.13.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.14.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.15.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.16.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.17.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.18.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.19.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.20.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.21.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.22.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.23.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.24.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.25.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.26.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.27.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.28.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.29.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.30.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.31.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.32.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.33.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.34.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.35.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.36.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.37.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.38.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.39.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.40.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.41.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.42.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.43.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.44.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.45.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.46.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.47.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.48.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.49.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.50.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.51.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.52.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.53.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.54.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.55.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.56.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.57.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.58.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.59.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.60.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.61.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.62.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.54.mlp.experts.63.gate_proj.weight": "model-00028-of-00136.safetensors", - "model.layers.55.input_layernorm.weight": "model-00028-of-00136.safetensors", - "model.layers.55.attention.query_key_value.weight": "model-00028-of-00136.safetensors", - "model.layers.55.mlp.experts.0.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.1.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.2.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.3.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.4.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.5.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.6.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.7.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.8.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.9.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.10.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.11.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.12.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.13.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.14.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.15.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.16.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.17.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.18.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.19.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.20.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.21.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.22.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.23.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.24.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.25.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.26.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.27.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.28.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.29.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.30.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.31.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.32.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.33.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.34.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.35.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.36.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.37.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.38.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.39.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.40.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.41.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.42.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.43.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.44.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.45.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.46.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.47.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.48.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.49.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.50.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.51.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.52.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.53.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.54.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.55.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.56.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.57.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.58.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.59.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.60.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.61.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.62.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.55.mlp.experts.63.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.input_layernorm.weight": "model-00029-of-00136.safetensors", - "model.layers.56.attention.query_key_value.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.0.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.1.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.2.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.3.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.4.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.5.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.6.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.7.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.8.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.9.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.10.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.11.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.12.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.13.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.14.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.15.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.16.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.17.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.18.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.19.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.20.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.21.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.22.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.23.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.24.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.25.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.26.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.27.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.28.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.29.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.30.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.31.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.32.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.33.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.34.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.35.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.36.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.37.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.38.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.39.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.40.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.41.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.42.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.43.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.44.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.45.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.46.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.47.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.48.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.49.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.50.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.51.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.52.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.53.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.54.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.55.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.56.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.57.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.58.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.59.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.60.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.61.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.62.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.56.mlp.experts.63.gate_proj.weight": "model-00029-of-00136.safetensors", - "model.layers.57.input_layernorm.weight": "model-00029-of-00136.safetensors", - "model.layers.57.attention.query_key_value.weight": "model-00029-of-00136.safetensors", - "model.layers.57.mlp.experts.0.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.1.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.2.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.3.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.4.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.5.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.6.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.7.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.8.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.9.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.10.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.11.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.12.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.13.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.14.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.15.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.16.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.17.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.18.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.19.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.20.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.21.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.22.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.23.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.24.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.25.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.26.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.27.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.28.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.29.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.30.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.31.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.32.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.33.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.34.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.35.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.36.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.37.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.38.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.39.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.40.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.41.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.42.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.43.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.44.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.45.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.46.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.47.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.48.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.49.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.50.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.51.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.52.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.53.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.54.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.55.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.56.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.57.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.58.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.59.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.60.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.61.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.62.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.57.mlp.experts.63.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.input_layernorm.weight": "model-00030-of-00136.safetensors", - "model.layers.58.attention.query_key_value.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.0.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.1.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.2.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.3.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.4.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.5.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.6.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.7.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.8.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.9.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.10.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.11.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.12.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.13.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.14.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.15.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.16.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.17.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.18.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.19.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.20.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.21.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.22.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.23.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.24.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.25.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.26.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.27.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.28.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.29.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.30.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.31.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.32.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.33.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.34.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.35.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.36.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.37.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.38.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.39.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.40.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.41.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.42.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.43.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.44.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.45.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.46.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.47.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.48.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.49.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.50.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.51.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.52.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.53.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.54.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.55.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.56.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.57.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.58.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.59.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.60.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.61.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.62.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.58.mlp.experts.63.gate_proj.weight": "model-00030-of-00136.safetensors", - "model.layers.59.input_layernorm.weight": "model-00030-of-00136.safetensors", - "model.layers.59.attention.query_key_value.weight": "model-00030-of-00136.safetensors", - "model.layers.59.mlp.experts.0.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.1.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.2.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.3.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.4.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.5.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.6.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.7.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.8.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.9.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.10.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.11.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.12.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.13.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.14.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.15.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.16.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.17.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.18.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.19.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.20.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.21.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.22.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.23.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.24.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.25.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.26.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.27.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.28.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.29.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.30.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.31.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.32.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.33.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.34.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.35.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.36.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.37.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.38.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.39.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.40.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.41.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.42.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.43.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.44.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.45.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.46.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.47.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.48.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.49.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.50.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.51.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.52.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.53.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.54.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.55.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.56.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.57.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.58.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.59.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.60.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.61.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.62.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.59.mlp.experts.63.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.input_layernorm.weight": "model-00031-of-00136.safetensors", - "model.layers.60.attention.query_key_value.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.0.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.1.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.2.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.3.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.4.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.5.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.6.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.7.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.8.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.9.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.10.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.11.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.12.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.13.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.14.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.15.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.16.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.17.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.18.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.19.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.20.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.21.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.22.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.23.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.24.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.25.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.26.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.27.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.28.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.29.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.30.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.31.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.32.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.33.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.34.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.35.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.36.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.37.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.38.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.39.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.40.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.41.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.42.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.43.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.44.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.45.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.46.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.47.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.48.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.49.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.50.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.51.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.52.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.53.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.54.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.55.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.56.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.57.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.58.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.59.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.60.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.61.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.62.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.60.mlp.experts.63.gate_proj.weight": "model-00031-of-00136.safetensors", - "model.layers.61.input_layernorm.weight": "model-00031-of-00136.safetensors", - "model.layers.61.attention.query_key_value.weight": "model-00031-of-00136.safetensors", - "model.layers.61.mlp.experts.0.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.1.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.2.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.3.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.4.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.5.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.6.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.7.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.8.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.9.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.10.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.11.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.12.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.13.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.14.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.15.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.16.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.17.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.18.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.19.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.20.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.21.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.22.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.23.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.24.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.25.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.26.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.27.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.28.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.29.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.30.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.31.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.32.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.33.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.34.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.35.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.36.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.37.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.38.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.39.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.40.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.41.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.42.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.43.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.44.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.45.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.46.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.47.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.48.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.49.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.50.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.51.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.52.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.53.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.54.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.55.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.56.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.57.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.58.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.59.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.60.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.61.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.62.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.61.mlp.experts.63.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.input_layernorm.weight": "model-00032-of-00136.safetensors", - "model.layers.62.attention.query_key_value.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.0.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.1.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.2.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.3.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.4.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.5.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.6.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.7.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.8.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.9.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.10.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.11.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.12.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.13.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.14.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.15.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.16.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.17.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.18.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.19.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.20.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.21.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.22.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.23.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.24.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.25.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.26.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.27.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.28.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.29.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.30.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.31.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.32.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.33.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.34.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.35.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.36.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.37.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.38.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.39.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.40.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.41.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.42.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.43.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.44.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.45.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.46.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.47.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.48.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.49.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.50.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.51.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.52.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.53.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.54.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.55.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.56.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.57.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.58.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.59.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.60.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.61.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.62.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.62.mlp.experts.63.gate_proj.weight": "model-00032-of-00136.safetensors", - "model.layers.63.input_layernorm.weight": "model-00032-of-00136.safetensors", - "model.layers.63.attention.query_key_value.weight": "model-00032-of-00136.safetensors", - "model.layers.63.mlp.experts.0.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.1.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.2.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.3.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.4.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.5.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.6.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.7.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.8.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.9.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.10.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.11.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.12.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.13.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.14.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.15.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.16.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.17.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.18.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.19.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.20.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.21.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.22.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.23.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.24.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.25.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.26.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.27.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.28.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.29.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.30.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.31.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.32.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.33.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.34.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.35.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.36.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.37.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.38.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.39.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.40.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.41.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.42.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.43.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.44.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.45.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.46.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.47.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.48.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.49.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.50.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.51.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.52.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.53.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.54.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.55.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.56.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.57.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.58.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.59.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.60.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.61.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.62.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.63.mlp.experts.63.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.input_layernorm.weight": "model-00033-of-00136.safetensors", - "model.layers.64.attention.query_key_value.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.0.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.1.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.2.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.3.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.4.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.5.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.6.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.7.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.8.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.9.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.10.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.11.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.12.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.13.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.14.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.15.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.16.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.17.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.18.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.19.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.20.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.21.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.22.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.23.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.24.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.25.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.26.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.27.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.28.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.29.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.30.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.31.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.32.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.33.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.34.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.35.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.36.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.37.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.38.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.39.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.40.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.41.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.42.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.43.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.44.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.45.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.46.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.47.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.48.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.49.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.50.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.51.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.52.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.53.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.54.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.55.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.56.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.57.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.58.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.59.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.60.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.61.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.62.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.64.mlp.experts.63.gate_proj.weight": "model-00033-of-00136.safetensors", - "model.layers.65.input_layernorm.weight": "model-00033-of-00136.safetensors", - "model.layers.65.attention.query_key_value.weight": "model-00033-of-00136.safetensors", - "model.layers.65.mlp.experts.0.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.1.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.2.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.3.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.4.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.5.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.6.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.7.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.8.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.9.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.10.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.11.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.12.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.13.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.14.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.15.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.16.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.17.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.18.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.19.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.20.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.21.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.22.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.23.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.24.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.25.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.26.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.27.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.28.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.29.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.30.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.31.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.32.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.33.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.34.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.35.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.36.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.37.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.38.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.39.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.40.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.41.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.42.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.43.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.44.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.45.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.46.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.47.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.48.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.49.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.50.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.51.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.52.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.53.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.54.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.55.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.56.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.57.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.58.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.59.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.60.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.61.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.62.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.65.mlp.experts.63.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.input_layernorm.weight": "model-00034-of-00136.safetensors", - "model.layers.66.attention.query_key_value.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.0.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.1.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.2.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.3.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.4.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.5.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.6.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.7.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.8.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.9.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.10.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.11.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.12.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.13.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.14.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.15.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.16.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.17.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.18.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.19.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.20.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.21.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.22.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.23.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.24.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.25.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.26.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.27.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.28.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.29.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.30.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.31.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.32.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.33.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.34.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.35.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.36.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.37.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.38.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.39.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.40.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.41.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.42.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.43.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.44.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.45.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.46.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.47.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.48.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.49.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.50.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.51.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.52.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.53.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.54.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.55.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.56.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.57.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.58.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.59.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.60.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.61.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.62.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.66.mlp.experts.63.gate_proj.weight": "model-00034-of-00136.safetensors", - "model.layers.67.input_layernorm.weight": "model-00034-of-00136.safetensors", - "model.layers.67.attention.query_key_value.weight": "model-00034-of-00136.safetensors", - "model.layers.67.mlp.experts.0.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.1.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.2.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.3.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.4.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.5.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.6.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.7.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.8.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.9.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.10.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.11.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.12.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.13.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.14.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.15.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.16.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.17.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.18.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.19.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.20.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.21.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.22.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.23.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.24.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.25.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.26.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.27.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.28.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.29.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.30.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.31.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.32.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.33.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.34.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.35.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.36.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.37.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.38.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.39.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.40.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.41.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.42.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.43.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.44.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.45.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.46.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.47.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.48.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.49.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.50.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.51.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.52.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.53.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.54.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.55.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.56.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.57.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.58.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.59.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.60.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.61.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.62.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.67.mlp.experts.63.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.input_layernorm.weight": "model-00035-of-00136.safetensors", - "model.layers.68.attention.query_key_value.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.0.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.1.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.2.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.3.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.4.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.5.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.6.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.7.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.8.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.9.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.10.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.11.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.12.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.13.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.14.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.15.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.16.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.17.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.18.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.19.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.20.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.21.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.22.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.23.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.24.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.25.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.26.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.27.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.28.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.29.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.30.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.31.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.32.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.33.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.34.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.35.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.36.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.37.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.38.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.39.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.40.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.41.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.42.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.43.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.44.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.45.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.46.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.47.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.48.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.49.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.50.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.51.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.52.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.53.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.54.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.55.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.56.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.57.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.58.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.59.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.60.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.61.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.62.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.68.mlp.experts.63.gate_proj.weight": "model-00035-of-00136.safetensors", - "model.layers.69.input_layernorm.weight": "model-00035-of-00136.safetensors", - "model.layers.69.attention.query_key_value.weight": "model-00035-of-00136.safetensors", - "model.layers.69.mlp.experts.0.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.1.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.2.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.3.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.4.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.5.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.6.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.7.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.8.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.9.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.10.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.11.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.12.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.13.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.14.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.15.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.16.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.17.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.18.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.19.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.20.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.21.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.22.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.23.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.24.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.25.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.26.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.27.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.28.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.29.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.30.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.31.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.32.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.33.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.34.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.35.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.36.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.37.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.38.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.39.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.40.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.41.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.42.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.43.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.44.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.45.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.46.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.47.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.48.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.49.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.50.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.51.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.52.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.53.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.54.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.55.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.56.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.57.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.58.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.59.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.60.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.61.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.62.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.69.mlp.experts.63.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.input_layernorm.weight": "model-00036-of-00136.safetensors", - "model.layers.70.attention.query_key_value.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.0.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.1.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.2.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.3.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.4.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.5.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.6.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.7.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.8.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.9.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.10.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.11.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.12.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.13.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.14.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.15.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.16.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.17.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.18.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.19.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.20.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.21.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.22.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.23.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.24.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.25.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.26.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.27.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.28.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.29.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.30.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.31.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.32.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.33.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.34.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.35.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.36.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.37.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.38.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.39.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.40.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.41.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.42.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.43.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.44.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.45.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.46.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.47.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.48.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.49.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.50.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.51.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.52.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.53.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.54.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.55.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.56.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.57.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.58.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.59.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.60.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.61.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.62.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.70.mlp.experts.63.gate_proj.weight": "model-00036-of-00136.safetensors", - "model.layers.71.input_layernorm.weight": "model-00036-of-00136.safetensors", - "model.layers.71.attention.query_key_value.weight": "model-00036-of-00136.safetensors", - "model.layers.71.mlp.experts.0.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.1.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.2.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.3.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.4.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.5.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.6.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.7.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.8.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.9.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.10.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.11.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.12.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.13.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.14.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.15.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.16.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.17.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.18.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.19.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.20.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.21.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.22.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.23.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.24.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.25.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.26.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.27.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.28.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.29.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.30.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.31.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.32.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.33.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.34.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.35.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.36.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.37.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.38.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.39.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.40.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.41.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.42.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.43.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.44.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.45.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.46.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.47.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.48.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.49.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.50.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.51.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.52.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.53.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.54.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.55.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.56.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.57.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.58.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.59.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.60.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.61.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.62.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.71.mlp.experts.63.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.input_layernorm.weight": "model-00037-of-00136.safetensors", - "model.layers.72.attention.query_key_value.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.0.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.1.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.2.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.3.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.4.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.5.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.6.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.7.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.8.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.9.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.10.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.11.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.12.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.13.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.14.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.15.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.16.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.17.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.18.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.19.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.20.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.21.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.22.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.23.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.24.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.25.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.26.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.27.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.28.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.29.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.30.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.31.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.32.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.33.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.34.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.35.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.36.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.37.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.38.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.39.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.40.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.41.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.42.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.43.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.44.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.45.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.46.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.47.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.48.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.49.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.50.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.51.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.52.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.53.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.54.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.55.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.56.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.57.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.58.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.59.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.60.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.61.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.62.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.72.mlp.experts.63.gate_proj.weight": "model-00037-of-00136.safetensors", - "model.layers.73.input_layernorm.weight": "model-00037-of-00136.safetensors", - "model.layers.73.attention.query_key_value.weight": "model-00037-of-00136.safetensors", - "model.layers.73.mlp.experts.0.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.1.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.2.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.3.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.4.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.5.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.6.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.7.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.8.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.9.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.10.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.11.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.12.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.13.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.14.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.15.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.16.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.17.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.18.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.19.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.20.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.21.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.22.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.23.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.24.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.25.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.26.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.27.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.28.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.29.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.30.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.31.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.32.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.33.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.34.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.35.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.36.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.37.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.38.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.39.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.40.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.41.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.42.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.43.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.44.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.45.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.46.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.47.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.48.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.49.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.50.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.51.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.52.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.53.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.54.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.55.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.56.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.57.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.58.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.59.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.60.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.61.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.62.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.73.mlp.experts.63.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.input_layernorm.weight": "model-00038-of-00136.safetensors", - "model.layers.74.attention.query_key_value.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.0.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.1.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.2.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.3.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.4.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.5.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.6.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.7.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.8.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.9.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.10.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.11.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.12.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.13.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.14.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.15.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.16.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.17.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.18.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.19.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.20.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.21.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.22.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.23.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.24.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.25.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.26.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.27.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.28.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.29.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.30.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.31.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.32.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.33.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.34.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.35.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.36.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.37.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.38.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.39.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.40.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.41.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.42.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.43.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.44.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.45.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.46.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.47.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.48.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.49.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.50.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.51.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.52.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.53.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.54.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.55.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.56.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.57.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.58.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.59.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.60.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.61.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.62.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.74.mlp.experts.63.gate_proj.weight": "model-00038-of-00136.safetensors", - "model.layers.75.input_layernorm.weight": "model-00038-of-00136.safetensors", - "model.layers.75.attention.query_key_value.weight": "model-00038-of-00136.safetensors", - "model.layers.75.mlp.experts.0.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.1.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.2.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.3.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.4.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.5.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.6.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.7.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.8.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.9.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.10.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.11.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.12.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.13.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.14.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.15.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.16.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.17.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.18.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.19.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.20.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.21.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.22.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.23.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.24.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.25.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.26.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.27.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.28.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.29.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.30.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.31.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.32.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.33.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.34.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.35.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.36.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.37.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.38.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.39.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.40.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.41.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.42.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.43.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.44.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.45.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.46.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.47.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.48.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.49.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.50.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.51.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.52.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.53.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.54.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.55.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.56.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.57.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.58.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.59.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.60.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.61.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.62.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.75.mlp.experts.63.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.input_layernorm.weight": "model-00039-of-00136.safetensors", - "model.layers.76.attention.query_key_value.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.0.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.1.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.2.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.3.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.4.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.5.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.6.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.7.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.8.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.9.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.10.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.11.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.12.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.13.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.14.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.15.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.16.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.17.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.18.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.19.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.20.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.21.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.22.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.23.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.24.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.25.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.26.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.27.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.28.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.29.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.30.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.31.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.32.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.33.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.34.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.35.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.36.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.37.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.38.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.39.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.40.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.41.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.42.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.43.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.44.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.45.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.46.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.47.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.48.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.49.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.50.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.51.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.52.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.53.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.54.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.55.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.56.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.57.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.58.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.59.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.60.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.61.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.62.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.76.mlp.experts.63.gate_proj.weight": "model-00039-of-00136.safetensors", - "model.layers.77.input_layernorm.weight": "model-00039-of-00136.safetensors", - "model.layers.77.attention.query_key_value.weight": "model-00039-of-00136.safetensors", - "model.layers.77.mlp.experts.0.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.1.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.2.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.3.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.4.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.5.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.6.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.7.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.8.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.9.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.10.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.11.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.12.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.13.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.14.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.15.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.16.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.17.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.18.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.19.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.20.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.21.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.22.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.23.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.24.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.25.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.26.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.27.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.28.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.29.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.30.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.31.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.32.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.33.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.34.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.35.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.36.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.37.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.38.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.39.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.40.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.41.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.42.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.43.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.44.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.45.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.46.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.47.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.48.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.49.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.50.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.51.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.52.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.53.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.54.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.55.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.56.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.57.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.58.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.59.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.60.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.61.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.62.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.77.mlp.experts.63.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.input_layernorm.weight": "model-00040-of-00136.safetensors", - "model.layers.78.attention.query_key_value.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.0.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.1.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.2.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.3.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.4.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.5.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.6.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.7.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.8.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.9.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.10.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.11.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.12.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.13.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.14.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.15.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.16.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.17.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.18.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.19.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.20.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.21.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.22.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.23.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.24.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.25.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.26.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.27.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.28.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.29.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.30.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.31.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.32.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.33.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.34.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.35.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.36.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.37.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.38.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.39.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.40.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.41.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.42.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.43.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.44.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.45.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.46.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.47.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.48.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.49.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.50.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.51.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.52.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.53.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.54.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.55.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.56.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.57.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.58.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.59.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.60.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.61.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.62.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.78.mlp.experts.63.gate_proj.weight": "model-00040-of-00136.safetensors", - "model.layers.79.input_layernorm.weight": "model-00040-of-00136.safetensors", - "model.layers.79.attention.query_key_value.weight": "model-00040-of-00136.safetensors", - "model.layers.79.mlp.experts.0.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.1.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.2.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.3.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.4.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.5.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.6.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.7.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.8.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.9.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.10.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.11.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.12.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.13.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.14.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.15.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.16.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.17.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.18.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.19.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.20.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.21.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.22.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.23.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.24.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.25.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.26.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.27.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.28.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.29.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.30.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.31.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.32.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.33.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.34.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.35.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.36.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.37.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.38.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.39.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.40.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.41.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.42.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.43.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.44.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.45.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.46.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.47.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.48.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.49.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.50.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.51.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.52.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.53.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.54.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.55.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.56.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.57.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.58.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.59.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.60.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.61.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.62.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.79.mlp.experts.63.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.input_layernorm.weight": "model-00041-of-00136.safetensors", - "model.layers.80.attention.query_key_value.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.0.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.1.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.2.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.3.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.4.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.5.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.6.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.7.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.8.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.9.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.10.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.11.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.12.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.13.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.14.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.15.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.16.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.17.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.18.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.19.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.20.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.21.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.22.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.23.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.24.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.25.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.26.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.27.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.28.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.29.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.30.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.31.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.32.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.33.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.34.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.35.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.36.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.37.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.38.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.39.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.40.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.41.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.42.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.43.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.44.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.45.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.46.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.47.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.48.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.49.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.50.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.51.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.52.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.53.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.54.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.55.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.56.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.57.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.58.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.59.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.60.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.61.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.62.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.80.mlp.experts.63.gate_proj.weight": "model-00041-of-00136.safetensors", - "model.layers.81.input_layernorm.weight": "model-00041-of-00136.safetensors", - "model.layers.81.attention.query_key_value.weight": "model-00041-of-00136.safetensors", - "model.layers.81.mlp.experts.0.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.1.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.2.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.3.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.4.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.5.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.6.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.7.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.8.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.9.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.10.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.11.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.12.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.13.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.14.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.15.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.16.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.17.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.18.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.19.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.20.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.21.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.22.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.23.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.24.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.25.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.26.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.27.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.28.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.29.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.30.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.31.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.32.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.33.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.34.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.35.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.36.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.37.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.38.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.39.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.40.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.41.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.42.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.43.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.44.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.45.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.46.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.47.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.48.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.49.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.50.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.51.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.52.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.53.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.54.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.55.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.56.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.57.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.58.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.59.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.60.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.61.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.62.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.81.mlp.experts.63.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.input_layernorm.weight": "model-00042-of-00136.safetensors", - "model.layers.82.attention.query_key_value.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.0.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.1.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.2.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.3.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.4.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.5.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.6.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.7.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.8.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.9.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.10.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.11.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.12.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.13.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.14.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.15.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.16.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.17.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.18.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.19.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.20.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.21.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.22.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.23.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.24.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.25.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.26.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.27.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.28.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.29.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.30.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.31.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.32.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.33.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.34.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.35.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.36.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.37.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.38.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.39.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.40.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.41.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.42.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.43.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.44.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.45.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.46.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.47.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.48.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.49.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.50.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.51.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.52.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.53.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.54.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.55.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.56.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.57.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.58.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.59.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.60.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.61.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.62.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.82.mlp.experts.63.gate_proj.weight": "model-00042-of-00136.safetensors", - "model.layers.83.input_layernorm.weight": "model-00042-of-00136.safetensors", - "model.layers.83.attention.query_key_value.weight": "model-00042-of-00136.safetensors", - "model.layers.83.mlp.experts.0.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.1.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.2.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.3.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.4.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.5.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.6.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.7.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.8.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.9.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.10.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.11.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.12.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.13.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.14.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.15.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.16.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.17.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.18.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.19.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.20.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.21.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.22.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.23.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.24.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.25.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.26.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.27.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.28.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.29.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.30.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.31.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.32.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.33.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.34.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.35.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.36.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.37.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.38.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.39.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.40.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.41.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.42.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.43.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.44.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.45.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.46.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.47.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.48.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.49.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.50.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.51.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.52.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.53.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.54.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.55.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.56.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.57.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.58.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.59.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.60.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.61.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.62.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.83.mlp.experts.63.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.input_layernorm.weight": "model-00043-of-00136.safetensors", - "model.layers.84.attention.query_key_value.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.0.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.1.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.2.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.3.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.4.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.5.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.6.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.7.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.8.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.9.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.10.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.11.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.12.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.13.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.14.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.15.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.16.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.17.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.18.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.19.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.20.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.21.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.22.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.23.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.24.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.25.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.26.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.27.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.28.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.29.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.30.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.31.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.32.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.33.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.34.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.35.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.36.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.37.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.38.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.39.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.40.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.41.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.42.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.43.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.44.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.45.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.46.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.47.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.48.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.49.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.50.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.51.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.52.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.53.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.54.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.55.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.56.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.57.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.58.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.59.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.60.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.61.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.62.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.84.mlp.experts.63.gate_proj.weight": "model-00043-of-00136.safetensors", - "model.layers.85.input_layernorm.weight": "model-00043-of-00136.safetensors", - "model.layers.85.attention.query_key_value.weight": "model-00043-of-00136.safetensors", - "model.layers.85.mlp.experts.0.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.1.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.2.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.3.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.4.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.5.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.6.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.7.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.8.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.9.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.10.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.11.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.12.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.13.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.14.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.15.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.16.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.17.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.18.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.19.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.20.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.21.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.22.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.23.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.24.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.25.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.26.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.27.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.28.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.29.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.30.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.31.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.32.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.33.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.34.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.35.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.36.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.37.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.38.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.39.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.40.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.41.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.42.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.43.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.44.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.45.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.46.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.47.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.48.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.49.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.50.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.51.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.52.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.53.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.54.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.55.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.56.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.57.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.58.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.59.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.60.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.61.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.62.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.85.mlp.experts.63.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.input_layernorm.weight": "model-00044-of-00136.safetensors", - "model.layers.86.attention.query_key_value.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.0.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.1.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.2.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.3.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.4.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.5.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.6.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.7.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.8.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.9.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.10.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.11.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.12.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.13.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.14.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.15.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.16.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.17.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.18.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.19.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.20.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.21.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.22.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.23.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.24.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.25.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.26.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.27.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.28.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.29.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.30.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.31.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.32.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.33.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.34.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.35.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.36.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.37.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.38.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.39.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.40.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.41.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.42.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.43.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.44.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.45.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.46.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.47.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.48.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.49.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.50.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.51.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.52.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.53.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.54.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.55.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.56.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.57.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.58.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.59.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.60.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.61.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.62.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.86.mlp.experts.63.gate_proj.weight": "model-00044-of-00136.safetensors", - "model.layers.87.input_layernorm.weight": "model-00044-of-00136.safetensors", - "model.layers.87.attention.query_key_value.weight": "model-00044-of-00136.safetensors", - "model.layers.87.mlp.experts.0.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.1.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.2.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.3.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.4.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.5.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.6.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.7.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.8.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.9.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.10.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.11.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.12.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.13.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.14.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.15.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.16.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.17.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.18.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.19.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.20.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.21.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.22.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.23.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.24.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.25.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.26.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.27.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.28.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.29.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.30.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.31.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.32.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.33.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.34.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.35.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.36.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.37.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.38.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.39.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.40.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.41.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.42.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.43.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.44.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.45.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.46.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.47.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.48.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.49.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.50.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.51.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.52.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.53.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.54.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.55.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.56.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.57.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.58.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.59.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.60.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.61.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.62.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.87.mlp.experts.63.gate_proj.weight": "model-00045-of-00136.safetensors", - "model.layers.0.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.1.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.2.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.3.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.4.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.5.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.6.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.7.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.8.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.9.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.10.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.11.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.12.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.13.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.14.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.15.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.16.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.17.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.18.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.19.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.20.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.21.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.22.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.23.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.24.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.25.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.26.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.27.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.28.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.29.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.30.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.31.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.32.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.33.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.34.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.35.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.36.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.37.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.38.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.39.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.40.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.41.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.42.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.43.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.44.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.45.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.46.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.47.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.48.attention.dense.weight": "model-00045-of-00136.safetensors", - "model.layers.49.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.50.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.51.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.52.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.53.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.54.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.55.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.56.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.57.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.58.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.59.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.60.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.61.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.62.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.63.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.64.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.65.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.66.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.67.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.68.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.69.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.70.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.71.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.72.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.73.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.74.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.75.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.76.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.77.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.78.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.79.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.80.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.81.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.82.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.83.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.84.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.85.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.86.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.87.attention.dense.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.0.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.1.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.2.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.3.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.4.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.5.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.6.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.7.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.8.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.9.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.10.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.11.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.12.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.13.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.14.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.15.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.16.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.17.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.18.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.19.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.20.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.21.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.22.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.23.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.24.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.25.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.26.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.27.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.28.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.29.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.30.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.31.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.32.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.33.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.34.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.35.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.36.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.37.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.38.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.39.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.40.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.41.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.42.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.43.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.44.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.45.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.46.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.47.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.48.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.49.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.50.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.51.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.52.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.53.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.54.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.55.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.56.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.57.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.58.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.59.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.60.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.61.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.62.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.0.mlp.experts.63.down_proj.weight": "model-00046-of-00136.safetensors", - "model.layers.1.mlp.experts.0.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.1.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.2.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.3.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.4.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.5.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.6.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.7.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.8.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.9.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.10.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.11.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.12.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.13.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.14.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.15.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.16.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.17.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.18.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.19.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.20.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.21.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.22.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.23.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.24.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.25.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.26.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.27.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.28.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.29.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.30.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.31.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.32.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.33.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.34.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.35.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.36.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.37.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.38.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.39.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.40.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.41.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.42.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.43.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.44.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.45.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.46.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.47.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.48.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.49.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.50.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.51.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.52.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.53.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.54.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.55.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.56.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.57.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.58.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.59.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.60.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.61.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.62.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.1.mlp.experts.63.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.0.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.1.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.2.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.3.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.4.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.5.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.6.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.7.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.8.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.9.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.10.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.11.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.12.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.13.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.14.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.15.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.16.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.17.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.18.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.19.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.20.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.21.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.22.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.23.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.24.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.25.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.26.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.27.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.28.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.29.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.30.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.31.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.32.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.33.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.34.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.35.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.36.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.37.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.38.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.39.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.40.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.41.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.42.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.43.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.44.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.45.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.46.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.47.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.48.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.49.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.50.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.51.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.52.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.53.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.54.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.55.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.56.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.57.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.58.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.59.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.60.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.61.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.62.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.2.mlp.experts.63.down_proj.weight": "model-00047-of-00136.safetensors", - "model.layers.3.mlp.experts.0.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.1.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.2.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.3.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.4.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.5.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.6.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.7.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.8.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.9.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.10.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.11.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.12.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.13.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.14.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.15.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.16.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.17.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.18.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.19.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.20.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.21.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.22.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.23.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.24.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.25.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.26.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.27.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.28.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.29.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.30.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.31.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.32.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.33.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.34.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.35.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.36.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.37.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.38.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.39.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.40.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.41.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.42.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.43.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.44.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.45.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.46.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.47.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.48.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.49.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.50.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.51.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.52.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.53.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.54.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.55.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.56.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.57.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.58.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.59.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.60.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.61.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.62.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.3.mlp.experts.63.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.0.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.1.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.2.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.3.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.4.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.5.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.6.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.7.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.8.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.9.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.10.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.11.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.12.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.13.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.14.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.15.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.16.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.17.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.18.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.19.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.20.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.21.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.22.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.23.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.24.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.25.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.26.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.27.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.28.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.29.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.30.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.31.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.32.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.33.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.34.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.35.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.36.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.37.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.38.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.39.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.40.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.41.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.42.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.43.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.44.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.45.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.46.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.47.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.48.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.49.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.50.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.51.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.52.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.53.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.54.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.55.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.56.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.57.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.58.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.59.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.60.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.61.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.62.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.4.mlp.experts.63.down_proj.weight": "model-00048-of-00136.safetensors", - "model.layers.5.mlp.experts.0.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.1.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.2.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.3.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.4.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.5.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.6.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.7.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.8.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.9.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.10.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.11.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.12.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.13.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.14.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.15.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.16.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.17.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.18.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.19.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.20.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.21.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.22.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.23.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.24.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.25.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.26.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.27.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.28.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.29.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.30.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.31.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.32.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.33.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.34.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.35.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.36.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.37.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.38.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.39.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.40.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.41.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.42.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.43.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.44.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.45.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.46.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.47.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.48.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.49.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.50.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.51.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.52.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.53.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.54.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.55.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.56.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.57.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.58.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.59.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.60.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.61.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.62.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.5.mlp.experts.63.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.0.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.1.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.2.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.3.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.4.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.5.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.6.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.7.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.8.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.9.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.10.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.11.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.12.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.13.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.14.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.15.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.16.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.17.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.18.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.19.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.20.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.21.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.22.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.23.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.24.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.25.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.26.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.27.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.28.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.29.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.30.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.31.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.32.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.33.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.34.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.35.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.36.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.37.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.38.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.39.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.40.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.41.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.42.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.43.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.44.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.45.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.46.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.47.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.48.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.49.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.50.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.51.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.52.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.53.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.54.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.55.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.56.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.57.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.58.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.59.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.60.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.61.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.62.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.6.mlp.experts.63.down_proj.weight": "model-00049-of-00136.safetensors", - "model.layers.7.mlp.experts.0.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.1.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.2.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.3.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.4.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.5.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.6.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.7.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.8.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.9.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.10.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.11.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.12.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.13.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.14.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.15.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.16.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.17.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.18.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.19.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.20.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.21.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.22.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.23.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.24.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.25.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.26.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.27.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.28.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.29.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.30.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.31.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.32.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.33.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.34.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.35.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.36.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.37.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.38.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.39.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.40.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.41.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.42.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.43.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.44.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.45.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.46.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.47.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.48.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.49.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.50.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.51.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.52.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.53.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.54.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.55.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.56.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.57.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.58.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.59.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.60.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.61.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.62.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.7.mlp.experts.63.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.0.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.1.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.2.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.3.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.4.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.5.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.6.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.7.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.8.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.9.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.10.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.11.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.12.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.13.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.14.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.15.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.16.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.17.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.18.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.19.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.20.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.21.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.22.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.23.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.24.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.25.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.26.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.27.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.28.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.29.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.30.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.31.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.32.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.33.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.34.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.35.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.36.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.37.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.38.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.39.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.40.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.41.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.42.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.43.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.44.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.45.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.46.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.47.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.48.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.49.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.50.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.51.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.52.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.53.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.54.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.55.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.56.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.57.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.58.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.59.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.60.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.61.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.62.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.8.mlp.experts.63.down_proj.weight": "model-00050-of-00136.safetensors", - "model.layers.9.mlp.experts.0.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.1.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.2.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.3.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.4.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.5.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.6.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.7.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.8.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.9.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.10.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.11.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.12.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.13.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.14.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.15.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.16.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.17.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.18.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.19.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.20.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.21.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.22.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.23.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.24.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.25.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.26.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.27.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.28.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.29.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.30.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.31.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.32.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.33.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.34.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.35.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.36.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.37.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.38.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.39.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.40.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.41.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.42.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.43.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.44.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.45.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.46.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.47.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.48.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.49.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.50.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.51.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.52.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.53.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.54.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.55.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.56.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.57.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.58.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.59.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.60.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.61.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.62.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.9.mlp.experts.63.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.0.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.1.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.2.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.3.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.4.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.5.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.6.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.7.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.8.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.9.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.10.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.11.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.12.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.13.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.14.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.15.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.16.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.17.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.18.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.19.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.20.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.21.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.22.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.23.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.24.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.25.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.26.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.27.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.28.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.29.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.30.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.31.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.32.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.33.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.34.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.35.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.36.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.37.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.38.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.39.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.40.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.41.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.42.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.43.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.44.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.45.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.46.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.47.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.48.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.49.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.50.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.51.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.52.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.53.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.54.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.55.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.56.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.57.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.58.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.59.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.60.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.61.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.62.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.10.mlp.experts.63.down_proj.weight": "model-00051-of-00136.safetensors", - "model.layers.11.mlp.experts.0.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.1.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.2.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.3.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.4.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.5.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.6.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.7.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.8.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.9.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.10.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.11.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.12.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.13.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.14.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.15.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.16.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.17.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.18.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.19.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.20.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.21.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.22.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.23.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.24.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.25.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.26.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.27.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.28.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.29.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.30.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.31.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.32.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.33.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.34.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.35.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.36.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.37.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.38.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.39.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.40.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.41.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.42.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.43.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.44.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.45.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.46.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.47.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.48.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.49.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.50.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.51.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.52.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.53.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.54.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.55.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.56.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.57.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.58.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.59.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.60.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.61.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.62.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.11.mlp.experts.63.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.0.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.1.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.2.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.3.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.4.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.5.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.6.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.7.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.8.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.9.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.10.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.11.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.12.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.13.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.14.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.15.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.16.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.17.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.18.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.19.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.20.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.21.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.22.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.23.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.24.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.25.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.26.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.27.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.28.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.29.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.30.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.31.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.32.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.33.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.34.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.35.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.36.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.37.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.38.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.39.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.40.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.41.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.42.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.43.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.44.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.45.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.46.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.47.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.48.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.49.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.50.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.51.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.52.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.53.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.54.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.55.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.56.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.57.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.58.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.59.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.60.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.61.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.62.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.12.mlp.experts.63.down_proj.weight": "model-00052-of-00136.safetensors", - "model.layers.13.mlp.experts.0.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.1.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.2.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.3.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.4.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.5.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.6.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.7.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.8.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.9.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.10.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.11.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.12.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.13.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.14.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.15.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.16.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.17.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.18.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.19.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.20.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.21.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.22.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.23.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.24.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.25.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.26.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.27.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.28.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.29.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.30.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.31.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.32.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.33.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.34.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.35.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.36.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.37.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.38.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.39.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.40.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.41.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.42.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.43.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.44.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.45.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.46.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.47.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.48.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.49.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.50.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.51.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.52.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.53.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.54.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.55.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.56.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.57.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.58.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.59.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.60.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.61.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.62.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.13.mlp.experts.63.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.0.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.1.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.2.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.3.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.4.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.5.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.6.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.7.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.8.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.9.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.10.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.11.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.12.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.13.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.14.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.15.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.16.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.17.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.18.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.19.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.20.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.21.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.22.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.23.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.24.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.25.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.26.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.27.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.28.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.29.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.30.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.31.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.32.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.33.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.34.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.35.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.36.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.37.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.38.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.39.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.40.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.41.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.42.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.43.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.44.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.45.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.46.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.47.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.48.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.49.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.50.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.51.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.52.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.53.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.54.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.55.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.56.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.57.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.58.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.59.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.60.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.61.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.62.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.14.mlp.experts.63.down_proj.weight": "model-00053-of-00136.safetensors", - "model.layers.15.mlp.experts.0.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.1.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.2.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.3.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.4.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.5.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.6.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.7.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.8.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.9.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.10.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.11.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.12.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.13.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.14.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.15.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.16.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.17.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.18.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.19.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.20.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.21.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.22.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.23.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.24.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.25.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.26.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.27.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.28.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.29.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.30.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.31.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.32.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.33.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.34.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.35.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.36.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.37.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.38.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.39.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.40.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.41.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.42.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.43.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.44.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.45.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.46.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.47.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.48.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.49.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.50.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.51.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.52.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.53.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.54.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.55.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.56.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.57.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.58.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.59.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.60.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.61.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.62.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.15.mlp.experts.63.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.0.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.1.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.2.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.3.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.4.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.5.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.6.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.7.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.8.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.9.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.10.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.11.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.12.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.13.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.14.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.15.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.16.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.17.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.18.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.19.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.20.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.21.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.22.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.23.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.24.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.25.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.26.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.27.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.28.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.29.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.30.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.31.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.32.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.33.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.34.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.35.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.36.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.37.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.38.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.39.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.40.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.41.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.42.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.43.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.44.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.45.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.46.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.47.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.48.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.49.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.50.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.51.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.52.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.53.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.54.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.55.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.56.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.57.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.58.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.59.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.60.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.61.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.62.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.16.mlp.experts.63.down_proj.weight": "model-00054-of-00136.safetensors", - "model.layers.17.mlp.experts.0.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.1.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.2.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.3.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.4.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.5.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.6.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.7.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.8.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.9.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.10.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.11.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.12.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.13.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.14.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.15.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.16.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.17.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.18.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.19.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.20.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.21.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.22.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.23.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.24.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.25.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.26.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.27.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.28.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.29.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.30.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.31.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.32.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.33.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.34.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.35.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.36.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.37.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.38.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.39.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.40.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.41.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.42.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.43.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.44.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.45.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.46.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.47.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.48.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.49.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.50.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.51.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.52.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.53.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.54.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.55.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.56.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.57.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.58.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.59.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.60.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.61.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.62.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.17.mlp.experts.63.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.0.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.1.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.2.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.3.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.4.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.5.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.6.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.7.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.8.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.9.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.10.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.11.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.12.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.13.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.14.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.15.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.16.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.17.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.18.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.19.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.20.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.21.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.22.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.23.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.24.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.25.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.26.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.27.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.28.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.29.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.30.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.31.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.32.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.33.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.34.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.35.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.36.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.37.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.38.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.39.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.40.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.41.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.42.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.43.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.44.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.45.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.46.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.47.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.48.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.49.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.50.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.51.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.52.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.53.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.54.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.55.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.56.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.57.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.58.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.59.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.60.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.61.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.62.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.18.mlp.experts.63.down_proj.weight": "model-00055-of-00136.safetensors", - "model.layers.19.mlp.experts.0.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.1.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.2.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.3.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.4.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.5.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.6.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.7.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.8.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.9.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.10.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.11.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.12.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.13.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.14.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.15.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.16.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.17.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.18.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.19.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.20.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.21.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.22.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.23.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.24.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.25.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.26.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.27.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.28.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.29.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.30.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.31.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.32.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.33.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.34.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.35.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.36.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.37.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.38.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.39.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.40.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.41.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.42.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.43.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.44.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.45.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.46.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.47.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.48.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.49.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.50.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.51.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.52.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.53.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.54.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.55.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.56.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.57.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.58.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.59.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.60.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.61.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.62.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.19.mlp.experts.63.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.0.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.1.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.2.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.3.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.4.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.5.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.6.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.7.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.8.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.9.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.10.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.11.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.12.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.13.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.14.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.15.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.16.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.17.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.18.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.19.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.20.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.21.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.22.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.23.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.24.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.25.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.26.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.27.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.28.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.29.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.30.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.31.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.32.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.33.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.34.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.35.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.36.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.37.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.38.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.39.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.40.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.41.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.42.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.43.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.44.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.45.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.46.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.47.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.48.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.49.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.50.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.51.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.52.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.53.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.54.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.55.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.56.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.57.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.58.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.59.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.60.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.61.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.62.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.20.mlp.experts.63.down_proj.weight": "model-00056-of-00136.safetensors", - "model.layers.21.mlp.experts.0.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.1.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.2.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.3.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.4.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.5.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.6.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.7.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.8.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.9.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.10.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.11.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.12.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.13.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.14.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.15.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.16.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.17.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.18.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.19.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.20.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.21.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.22.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.23.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.24.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.25.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.26.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.27.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.28.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.29.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.30.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.31.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.32.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.33.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.34.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.35.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.36.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.37.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.38.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.39.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.40.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.41.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.42.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.43.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.44.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.45.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.46.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.47.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.48.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.49.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.50.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.51.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.52.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.53.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.54.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.55.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.56.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.57.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.58.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.59.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.60.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.61.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.62.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.21.mlp.experts.63.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.0.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.1.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.2.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.3.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.4.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.5.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.6.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.7.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.8.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.9.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.10.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.11.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.12.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.13.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.14.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.15.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.16.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.17.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.18.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.19.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.20.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.21.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.22.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.23.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.24.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.25.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.26.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.27.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.28.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.29.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.30.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.31.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.32.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.33.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.34.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.35.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.36.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.37.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.38.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.39.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.40.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.41.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.42.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.43.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.44.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.45.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.46.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.47.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.48.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.49.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.50.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.51.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.52.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.53.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.54.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.55.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.56.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.57.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.58.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.59.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.60.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.61.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.62.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.22.mlp.experts.63.down_proj.weight": "model-00057-of-00136.safetensors", - "model.layers.23.mlp.experts.0.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.1.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.2.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.3.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.4.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.5.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.6.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.7.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.8.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.9.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.10.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.11.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.12.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.13.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.14.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.15.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.16.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.17.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.18.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.19.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.20.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.21.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.22.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.23.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.24.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.25.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.26.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.27.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.28.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.29.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.30.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.31.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.32.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.33.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.34.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.35.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.36.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.37.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.38.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.39.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.40.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.41.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.42.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.43.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.44.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.45.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.46.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.47.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.48.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.49.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.50.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.51.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.52.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.53.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.54.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.55.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.56.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.57.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.58.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.59.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.60.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.61.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.62.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.23.mlp.experts.63.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.0.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.1.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.2.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.3.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.4.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.5.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.6.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.7.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.8.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.9.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.10.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.11.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.12.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.13.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.14.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.15.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.16.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.17.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.18.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.19.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.20.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.21.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.22.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.23.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.24.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.25.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.26.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.27.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.28.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.29.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.30.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.31.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.32.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.33.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.34.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.35.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.36.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.37.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.38.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.39.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.40.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.41.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.42.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.43.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.44.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.45.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.46.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.47.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.48.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.49.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.50.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.51.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.52.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.53.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.54.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.55.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.56.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.57.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.58.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.59.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.60.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.61.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.62.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.24.mlp.experts.63.down_proj.weight": "model-00058-of-00136.safetensors", - "model.layers.25.mlp.experts.0.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.1.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.2.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.3.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.4.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.5.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.6.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.7.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.8.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.9.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.10.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.11.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.12.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.13.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.14.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.15.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.16.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.17.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.18.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.19.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.20.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.21.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.22.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.23.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.24.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.25.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.26.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.27.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.28.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.29.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.30.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.31.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.32.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.33.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.34.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.35.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.36.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.37.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.38.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.39.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.40.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.41.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.42.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.43.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.44.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.45.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.46.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.47.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.48.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.49.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.50.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.51.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.52.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.53.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.54.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.55.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.56.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.57.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.58.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.59.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.60.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.61.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.62.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.25.mlp.experts.63.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.0.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.1.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.2.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.3.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.4.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.5.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.6.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.7.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.8.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.9.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.10.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.11.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.12.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.13.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.14.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.15.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.16.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.17.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.18.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.19.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.20.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.21.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.22.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.23.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.24.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.25.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.26.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.27.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.28.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.29.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.30.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.31.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.32.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.33.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.34.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.35.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.36.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.37.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.38.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.39.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.40.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.41.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.42.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.43.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.44.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.45.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.46.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.47.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.48.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.49.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.50.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.51.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.52.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.53.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.54.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.55.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.56.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.57.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.58.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.59.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.60.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.61.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.62.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.26.mlp.experts.63.down_proj.weight": "model-00059-of-00136.safetensors", - "model.layers.27.mlp.experts.0.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.1.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.2.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.3.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.4.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.5.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.6.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.7.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.8.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.9.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.10.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.11.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.12.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.13.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.14.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.15.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.16.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.17.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.18.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.19.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.20.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.21.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.22.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.23.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.24.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.25.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.26.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.27.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.28.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.29.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.30.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.31.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.32.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.33.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.34.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.35.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.36.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.37.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.38.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.39.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.40.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.41.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.42.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.43.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.44.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.45.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.46.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.47.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.48.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.49.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.50.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.51.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.52.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.53.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.54.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.55.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.56.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.57.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.58.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.59.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.60.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.61.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.62.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.27.mlp.experts.63.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.0.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.1.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.2.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.3.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.4.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.5.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.6.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.7.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.8.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.9.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.10.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.11.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.12.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.13.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.14.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.15.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.16.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.17.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.18.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.19.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.20.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.21.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.22.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.23.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.24.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.25.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.26.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.27.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.28.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.29.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.30.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.31.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.32.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.33.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.34.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.35.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.36.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.37.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.38.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.39.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.40.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.41.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.42.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.43.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.44.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.45.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.46.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.47.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.48.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.49.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.50.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.51.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.52.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.53.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.54.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.55.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.56.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.57.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.58.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.59.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.60.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.61.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.62.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.28.mlp.experts.63.down_proj.weight": "model-00060-of-00136.safetensors", - "model.layers.29.mlp.experts.0.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.1.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.2.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.3.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.4.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.5.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.6.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.7.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.8.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.9.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.10.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.11.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.12.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.13.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.14.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.15.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.16.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.17.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.18.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.19.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.20.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.21.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.22.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.23.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.24.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.25.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.26.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.27.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.28.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.29.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.30.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.31.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.32.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.33.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.34.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.35.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.36.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.37.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.38.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.39.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.40.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.41.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.42.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.43.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.44.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.45.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.46.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.47.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.48.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.49.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.50.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.51.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.52.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.53.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.54.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.55.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.56.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.57.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.58.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.59.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.60.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.61.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.62.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.29.mlp.experts.63.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.0.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.1.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.2.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.3.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.4.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.5.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.6.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.7.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.8.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.9.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.10.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.11.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.12.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.13.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.14.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.15.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.16.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.17.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.18.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.19.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.20.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.21.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.22.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.23.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.24.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.25.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.26.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.27.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.28.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.29.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.30.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.31.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.32.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.33.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.34.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.35.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.36.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.37.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.38.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.39.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.40.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.41.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.42.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.43.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.44.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.45.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.46.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.47.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.48.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.49.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.50.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.51.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.52.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.53.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.54.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.55.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.56.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.57.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.58.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.59.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.60.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.61.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.62.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.30.mlp.experts.63.down_proj.weight": "model-00061-of-00136.safetensors", - "model.layers.31.mlp.experts.0.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.1.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.2.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.3.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.4.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.5.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.6.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.7.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.8.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.9.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.10.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.11.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.12.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.13.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.14.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.15.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.16.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.17.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.18.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.19.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.20.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.21.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.22.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.23.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.24.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.25.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.26.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.27.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.28.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.29.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.30.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.31.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.32.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.33.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.34.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.35.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.36.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.37.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.38.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.39.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.40.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.41.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.42.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.43.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.44.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.45.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.46.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.47.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.48.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.49.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.50.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.51.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.52.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.53.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.54.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.55.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.56.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.57.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.58.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.59.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.60.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.61.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.62.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.31.mlp.experts.63.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.0.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.1.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.2.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.3.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.4.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.5.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.6.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.7.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.8.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.9.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.10.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.11.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.12.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.13.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.14.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.15.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.16.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.17.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.18.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.19.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.20.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.21.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.22.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.23.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.24.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.25.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.26.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.27.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.28.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.29.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.30.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.31.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.32.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.33.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.34.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.35.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.36.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.37.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.38.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.39.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.40.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.41.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.42.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.43.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.44.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.45.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.46.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.47.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.48.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.49.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.50.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.51.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.52.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.53.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.54.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.55.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.56.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.57.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.58.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.59.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.60.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.61.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.62.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.32.mlp.experts.63.down_proj.weight": "model-00062-of-00136.safetensors", - "model.layers.33.mlp.experts.0.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.1.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.2.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.3.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.4.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.5.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.6.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.7.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.8.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.9.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.10.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.11.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.12.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.13.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.14.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.15.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.16.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.17.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.18.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.19.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.20.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.21.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.22.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.23.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.24.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.25.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.26.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.27.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.28.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.29.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.30.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.31.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.32.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.33.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.34.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.35.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.36.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.37.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.38.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.39.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.40.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.41.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.42.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.43.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.44.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.45.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.46.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.47.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.48.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.49.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.50.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.51.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.52.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.53.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.54.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.55.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.56.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.57.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.58.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.59.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.60.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.61.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.62.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.33.mlp.experts.63.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.0.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.1.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.2.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.3.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.4.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.5.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.6.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.7.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.8.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.9.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.10.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.11.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.12.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.13.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.14.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.15.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.16.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.17.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.18.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.19.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.20.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.21.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.22.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.23.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.24.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.25.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.26.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.27.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.28.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.29.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.30.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.31.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.32.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.33.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.34.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.35.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.36.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.37.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.38.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.39.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.40.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.41.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.42.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.43.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.44.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.45.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.46.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.47.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.48.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.49.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.50.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.51.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.52.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.53.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.54.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.55.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.56.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.57.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.58.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.59.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.60.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.61.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.62.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.34.mlp.experts.63.down_proj.weight": "model-00063-of-00136.safetensors", - "model.layers.35.mlp.experts.0.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.1.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.2.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.3.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.4.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.5.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.6.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.7.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.8.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.9.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.10.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.11.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.12.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.13.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.14.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.15.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.16.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.17.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.18.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.19.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.20.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.21.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.22.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.23.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.24.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.25.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.26.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.27.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.28.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.29.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.30.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.31.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.32.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.33.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.34.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.35.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.36.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.37.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.38.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.39.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.40.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.41.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.42.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.43.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.44.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.45.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.46.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.47.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.48.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.49.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.50.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.51.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.52.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.53.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.54.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.55.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.56.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.57.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.58.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.59.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.60.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.61.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.62.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.35.mlp.experts.63.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.0.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.1.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.2.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.3.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.4.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.5.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.6.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.7.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.8.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.9.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.10.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.11.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.12.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.13.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.14.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.15.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.16.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.17.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.18.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.19.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.20.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.21.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.22.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.23.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.24.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.25.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.26.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.27.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.28.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.29.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.30.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.31.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.32.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.33.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.34.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.35.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.36.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.37.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.38.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.39.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.40.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.41.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.42.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.43.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.44.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.45.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.46.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.47.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.48.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.49.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.50.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.51.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.52.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.53.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.54.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.55.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.56.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.57.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.58.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.59.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.60.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.61.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.62.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.36.mlp.experts.63.down_proj.weight": "model-00064-of-00136.safetensors", - "model.layers.37.mlp.experts.0.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.1.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.2.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.3.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.4.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.5.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.6.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.7.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.8.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.9.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.10.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.11.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.12.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.13.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.14.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.15.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.16.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.17.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.18.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.19.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.20.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.21.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.22.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.23.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.24.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.25.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.26.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.27.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.28.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.29.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.30.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.31.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.32.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.33.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.34.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.35.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.36.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.37.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.38.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.39.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.40.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.41.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.42.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.43.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.44.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.45.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.46.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.47.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.48.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.49.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.50.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.51.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.52.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.53.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.54.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.55.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.56.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.57.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.58.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.59.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.60.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.61.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.62.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.37.mlp.experts.63.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.0.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.1.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.2.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.3.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.4.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.5.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.6.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.7.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.8.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.9.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.10.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.11.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.12.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.13.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.14.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.15.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.16.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.17.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.18.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.19.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.20.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.21.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.22.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.23.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.24.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.25.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.26.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.27.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.28.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.29.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.30.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.31.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.32.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.33.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.34.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.35.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.36.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.37.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.38.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.39.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.40.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.41.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.42.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.43.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.44.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.45.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.46.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.47.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.48.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.49.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.50.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.51.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.52.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.53.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.54.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.55.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.56.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.57.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.58.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.59.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.60.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.61.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.62.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.38.mlp.experts.63.down_proj.weight": "model-00065-of-00136.safetensors", - "model.layers.39.mlp.experts.0.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.1.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.2.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.3.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.4.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.5.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.6.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.7.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.8.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.9.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.10.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.11.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.12.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.13.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.14.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.15.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.16.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.17.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.18.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.19.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.20.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.21.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.22.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.23.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.24.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.25.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.26.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.27.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.28.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.29.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.30.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.31.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.32.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.33.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.34.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.35.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.36.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.37.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.38.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.39.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.40.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.41.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.42.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.43.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.44.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.45.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.46.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.47.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.48.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.49.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.50.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.51.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.52.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.53.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.54.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.55.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.56.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.57.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.58.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.59.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.60.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.61.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.62.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.39.mlp.experts.63.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.0.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.1.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.2.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.3.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.4.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.5.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.6.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.7.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.8.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.9.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.10.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.11.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.12.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.13.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.14.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.15.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.16.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.17.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.18.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.19.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.20.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.21.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.22.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.23.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.24.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.25.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.26.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.27.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.28.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.29.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.30.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.31.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.32.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.33.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.34.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.35.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.36.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.37.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.38.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.39.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.40.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.41.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.42.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.43.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.44.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.45.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.46.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.47.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.48.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.49.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.50.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.51.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.52.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.53.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.54.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.55.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.56.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.57.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.58.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.59.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.60.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.61.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.62.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.40.mlp.experts.63.down_proj.weight": "model-00066-of-00136.safetensors", - "model.layers.41.mlp.experts.0.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.1.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.2.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.3.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.4.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.5.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.6.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.7.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.8.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.9.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.10.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.11.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.12.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.13.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.14.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.15.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.16.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.17.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.18.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.19.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.20.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.21.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.22.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.23.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.24.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.25.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.26.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.27.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.28.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.29.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.30.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.31.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.32.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.33.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.34.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.35.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.36.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.37.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.38.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.39.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.40.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.41.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.42.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.43.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.44.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.45.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.46.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.47.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.48.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.49.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.50.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.51.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.52.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.53.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.54.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.55.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.56.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.57.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.58.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.59.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.60.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.61.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.62.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.41.mlp.experts.63.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.0.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.1.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.2.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.3.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.4.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.5.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.6.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.7.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.8.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.9.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.10.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.11.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.12.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.13.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.14.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.15.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.16.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.17.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.18.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.19.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.20.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.21.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.22.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.23.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.24.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.25.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.26.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.27.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.28.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.29.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.30.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.31.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.32.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.33.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.34.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.35.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.36.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.37.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.38.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.39.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.40.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.41.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.42.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.43.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.44.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.45.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.46.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.47.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.48.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.49.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.50.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.51.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.52.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.53.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.54.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.55.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.56.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.57.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.58.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.59.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.60.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.61.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.62.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.42.mlp.experts.63.down_proj.weight": "model-00067-of-00136.safetensors", - "model.layers.43.mlp.experts.0.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.1.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.2.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.3.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.4.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.5.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.6.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.7.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.8.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.9.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.10.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.11.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.12.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.13.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.14.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.15.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.16.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.17.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.18.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.19.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.20.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.21.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.22.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.23.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.24.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.25.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.26.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.27.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.28.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.29.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.30.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.31.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.32.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.33.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.34.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.35.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.36.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.37.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.38.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.39.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.40.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.41.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.42.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.43.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.44.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.45.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.46.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.47.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.48.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.49.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.50.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.51.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.52.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.53.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.54.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.55.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.56.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.57.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.58.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.59.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.60.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.61.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.62.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.43.mlp.experts.63.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.0.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.1.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.2.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.3.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.4.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.5.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.6.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.7.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.8.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.9.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.10.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.11.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.12.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.13.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.14.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.15.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.16.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.17.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.18.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.19.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.20.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.21.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.22.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.23.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.24.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.25.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.26.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.27.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.28.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.29.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.30.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.31.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.32.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.33.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.34.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.35.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.36.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.37.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.38.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.39.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.40.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.41.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.42.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.43.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.44.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.45.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.46.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.47.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.48.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.49.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.50.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.51.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.52.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.53.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.54.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.55.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.56.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.57.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.58.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.59.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.60.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.61.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.62.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.44.mlp.experts.63.down_proj.weight": "model-00068-of-00136.safetensors", - "model.layers.45.mlp.experts.0.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.1.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.2.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.3.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.4.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.5.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.6.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.7.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.8.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.9.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.10.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.11.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.12.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.13.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.14.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.15.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.16.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.17.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.18.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.19.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.20.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.21.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.22.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.23.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.24.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.25.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.26.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.27.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.28.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.29.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.30.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.31.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.32.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.33.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.34.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.35.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.36.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.37.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.38.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.39.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.40.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.41.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.42.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.43.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.44.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.45.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.46.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.47.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.48.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.49.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.50.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.51.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.52.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.53.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.54.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.55.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.56.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.57.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.58.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.59.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.60.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.61.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.62.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.45.mlp.experts.63.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.0.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.1.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.2.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.3.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.4.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.5.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.6.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.7.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.8.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.9.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.10.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.11.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.12.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.13.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.14.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.15.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.16.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.17.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.18.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.19.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.20.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.21.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.22.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.23.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.24.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.25.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.26.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.27.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.28.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.29.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.30.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.31.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.32.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.33.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.34.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.35.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.36.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.37.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.38.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.39.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.40.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.41.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.42.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.43.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.44.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.45.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.46.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.47.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.48.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.49.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.50.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.51.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.52.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.53.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.54.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.55.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.56.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.57.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.58.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.59.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.60.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.61.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.62.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.46.mlp.experts.63.down_proj.weight": "model-00069-of-00136.safetensors", - "model.layers.47.mlp.experts.0.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.1.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.2.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.3.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.4.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.5.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.6.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.7.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.8.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.9.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.10.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.11.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.12.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.13.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.14.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.15.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.16.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.17.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.18.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.19.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.20.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.21.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.22.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.23.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.24.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.25.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.26.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.27.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.28.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.29.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.30.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.31.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.32.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.33.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.34.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.35.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.36.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.37.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.38.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.39.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.40.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.41.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.42.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.43.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.44.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.45.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.46.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.47.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.48.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.49.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.50.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.51.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.52.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.53.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.54.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.55.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.56.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.57.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.58.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.59.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.60.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.61.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.62.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.47.mlp.experts.63.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.0.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.1.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.2.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.3.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.4.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.5.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.6.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.7.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.8.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.9.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.10.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.11.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.12.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.13.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.14.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.15.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.16.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.17.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.18.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.19.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.20.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.21.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.22.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.23.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.24.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.25.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.26.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.27.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.28.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.29.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.30.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.31.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.32.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.33.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.34.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.35.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.36.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.37.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.38.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.39.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.40.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.41.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.42.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.43.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.44.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.45.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.46.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.47.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.48.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.49.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.50.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.51.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.52.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.53.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.54.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.55.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.56.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.57.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.58.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.59.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.60.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.61.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.62.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.48.mlp.experts.63.down_proj.weight": "model-00070-of-00136.safetensors", - "model.layers.49.mlp.experts.0.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.1.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.2.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.3.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.4.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.5.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.6.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.7.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.8.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.9.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.10.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.11.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.12.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.13.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.14.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.15.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.16.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.17.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.18.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.19.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.20.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.21.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.22.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.23.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.24.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.25.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.26.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.27.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.28.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.29.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.30.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.31.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.32.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.33.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.34.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.35.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.36.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.37.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.38.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.39.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.40.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.41.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.42.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.43.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.44.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.45.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.46.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.47.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.48.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.49.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.50.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.51.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.52.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.53.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.54.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.55.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.56.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.57.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.58.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.59.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.60.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.61.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.62.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.49.mlp.experts.63.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.0.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.1.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.2.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.3.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.4.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.5.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.6.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.7.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.8.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.9.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.10.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.11.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.12.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.13.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.14.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.15.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.16.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.17.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.18.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.19.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.20.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.21.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.22.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.23.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.24.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.25.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.26.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.27.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.28.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.29.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.30.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.31.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.32.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.33.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.34.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.35.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.36.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.37.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.38.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.39.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.40.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.41.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.42.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.43.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.44.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.45.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.46.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.47.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.48.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.49.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.50.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.51.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.52.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.53.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.54.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.55.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.56.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.57.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.58.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.59.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.60.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.61.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.62.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.50.mlp.experts.63.down_proj.weight": "model-00071-of-00136.safetensors", - "model.layers.51.mlp.experts.0.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.1.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.2.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.3.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.4.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.5.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.6.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.7.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.8.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.9.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.10.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.11.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.12.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.13.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.14.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.15.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.16.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.17.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.18.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.19.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.20.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.21.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.22.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.23.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.24.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.25.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.26.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.27.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.28.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.29.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.30.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.31.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.32.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.33.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.34.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.35.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.36.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.37.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.38.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.39.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.40.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.41.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.42.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.43.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.44.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.45.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.46.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.47.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.48.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.49.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.50.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.51.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.52.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.53.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.54.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.55.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.56.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.57.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.58.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.59.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.60.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.61.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.62.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.51.mlp.experts.63.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.0.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.1.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.2.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.3.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.4.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.5.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.6.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.7.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.8.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.9.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.10.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.11.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.12.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.13.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.14.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.15.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.16.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.17.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.18.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.19.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.20.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.21.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.22.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.23.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.24.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.25.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.26.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.27.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.28.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.29.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.30.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.31.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.32.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.33.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.34.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.35.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.36.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.37.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.38.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.39.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.40.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.41.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.42.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.43.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.44.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.45.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.46.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.47.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.48.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.49.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.50.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.51.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.52.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.53.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.54.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.55.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.56.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.57.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.58.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.59.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.60.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.61.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.62.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.52.mlp.experts.63.down_proj.weight": "model-00072-of-00136.safetensors", - "model.layers.53.mlp.experts.0.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.1.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.2.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.3.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.4.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.5.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.6.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.7.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.8.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.9.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.10.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.11.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.12.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.13.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.14.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.15.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.16.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.17.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.18.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.19.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.20.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.21.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.22.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.23.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.24.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.25.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.26.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.27.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.28.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.29.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.30.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.31.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.32.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.33.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.34.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.35.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.36.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.37.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.38.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.39.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.40.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.41.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.42.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.43.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.44.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.45.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.46.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.47.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.48.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.49.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.50.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.51.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.52.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.53.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.54.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.55.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.56.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.57.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.58.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.59.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.60.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.61.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.62.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.53.mlp.experts.63.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.0.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.1.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.2.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.3.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.4.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.5.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.6.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.7.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.8.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.9.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.10.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.11.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.12.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.13.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.14.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.15.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.16.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.17.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.18.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.19.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.20.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.21.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.22.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.23.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.24.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.25.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.26.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.27.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.28.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.29.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.30.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.31.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.32.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.33.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.34.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.35.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.36.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.37.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.38.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.39.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.40.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.41.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.42.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.43.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.44.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.45.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.46.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.47.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.48.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.49.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.50.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.51.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.52.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.53.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.54.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.55.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.56.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.57.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.58.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.59.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.60.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.61.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.62.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.54.mlp.experts.63.down_proj.weight": "model-00073-of-00136.safetensors", - "model.layers.55.mlp.experts.0.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.1.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.2.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.3.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.4.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.5.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.6.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.7.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.8.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.9.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.10.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.11.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.12.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.13.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.14.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.15.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.16.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.17.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.18.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.19.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.20.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.21.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.22.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.23.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.24.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.25.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.26.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.27.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.28.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.29.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.30.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.31.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.32.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.33.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.34.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.35.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.36.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.37.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.38.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.39.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.40.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.41.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.42.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.43.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.44.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.45.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.46.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.47.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.48.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.49.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.50.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.51.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.52.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.53.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.54.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.55.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.56.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.57.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.58.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.59.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.60.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.61.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.62.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.55.mlp.experts.63.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.0.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.1.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.2.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.3.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.4.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.5.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.6.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.7.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.8.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.9.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.10.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.11.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.12.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.13.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.14.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.15.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.16.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.17.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.18.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.19.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.20.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.21.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.22.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.23.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.24.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.25.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.26.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.27.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.28.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.29.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.30.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.31.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.32.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.33.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.34.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.35.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.36.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.37.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.38.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.39.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.40.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.41.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.42.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.43.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.44.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.45.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.46.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.47.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.48.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.49.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.50.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.51.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.52.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.53.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.54.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.55.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.56.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.57.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.58.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.59.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.60.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.61.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.62.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.56.mlp.experts.63.down_proj.weight": "model-00074-of-00136.safetensors", - "model.layers.57.mlp.experts.0.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.1.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.2.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.3.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.4.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.5.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.6.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.7.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.8.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.9.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.10.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.11.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.12.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.13.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.14.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.15.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.16.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.17.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.18.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.19.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.20.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.21.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.22.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.23.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.24.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.25.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.26.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.27.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.28.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.29.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.30.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.31.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.32.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.33.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.34.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.35.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.36.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.37.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.38.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.39.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.40.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.41.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.42.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.43.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.44.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.45.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.46.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.47.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.48.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.49.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.50.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.51.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.52.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.53.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.54.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.55.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.56.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.57.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.58.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.59.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.60.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.61.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.62.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.57.mlp.experts.63.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.0.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.1.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.2.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.3.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.4.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.5.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.6.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.7.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.8.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.9.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.10.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.11.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.12.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.13.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.14.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.15.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.16.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.17.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.18.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.19.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.20.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.21.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.22.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.23.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.24.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.25.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.26.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.27.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.28.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.29.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.30.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.31.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.32.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.33.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.34.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.35.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.36.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.37.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.38.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.39.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.40.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.41.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.42.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.43.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.44.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.45.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.46.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.47.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.48.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.49.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.50.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.51.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.52.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.53.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.54.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.55.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.56.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.57.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.58.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.59.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.60.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.61.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.62.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.58.mlp.experts.63.down_proj.weight": "model-00075-of-00136.safetensors", - "model.layers.59.mlp.experts.0.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.1.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.2.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.3.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.4.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.5.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.6.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.7.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.8.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.9.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.10.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.11.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.12.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.13.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.14.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.15.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.16.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.17.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.18.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.19.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.20.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.21.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.22.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.23.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.24.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.25.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.26.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.27.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.28.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.29.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.30.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.31.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.32.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.33.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.34.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.35.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.36.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.37.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.38.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.39.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.40.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.41.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.42.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.43.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.44.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.45.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.46.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.47.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.48.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.49.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.50.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.51.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.52.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.53.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.54.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.55.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.56.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.57.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.58.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.59.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.60.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.61.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.62.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.59.mlp.experts.63.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.0.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.1.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.2.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.3.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.4.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.5.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.6.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.7.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.8.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.9.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.10.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.11.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.12.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.13.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.14.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.15.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.16.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.17.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.18.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.19.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.20.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.21.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.22.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.23.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.24.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.25.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.26.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.27.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.28.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.29.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.30.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.31.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.32.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.33.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.34.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.35.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.36.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.37.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.38.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.39.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.40.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.41.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.42.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.43.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.44.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.45.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.46.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.47.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.48.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.49.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.50.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.51.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.52.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.53.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.54.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.55.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.56.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.57.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.58.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.59.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.60.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.61.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.62.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.60.mlp.experts.63.down_proj.weight": "model-00076-of-00136.safetensors", - "model.layers.61.mlp.experts.0.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.1.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.2.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.3.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.4.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.5.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.6.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.7.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.8.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.9.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.10.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.11.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.12.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.13.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.14.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.15.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.16.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.17.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.18.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.19.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.20.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.21.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.22.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.23.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.24.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.25.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.26.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.27.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.28.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.29.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.30.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.31.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.32.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.33.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.34.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.35.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.36.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.37.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.38.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.39.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.40.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.41.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.42.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.43.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.44.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.45.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.46.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.47.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.48.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.49.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.50.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.51.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.52.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.53.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.54.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.55.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.56.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.57.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.58.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.59.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.60.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.61.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.62.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.61.mlp.experts.63.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.0.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.1.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.2.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.3.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.4.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.5.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.6.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.7.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.8.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.9.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.10.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.11.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.12.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.13.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.14.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.15.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.16.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.17.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.18.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.19.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.20.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.21.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.22.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.23.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.24.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.25.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.26.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.27.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.28.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.29.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.30.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.31.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.32.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.33.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.34.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.35.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.36.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.37.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.38.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.39.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.40.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.41.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.42.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.43.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.44.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.45.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.46.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.47.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.48.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.49.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.50.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.51.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.52.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.53.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.54.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.55.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.56.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.57.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.58.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.59.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.60.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.61.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.62.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.62.mlp.experts.63.down_proj.weight": "model-00077-of-00136.safetensors", - "model.layers.63.mlp.experts.0.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.1.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.2.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.3.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.4.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.5.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.6.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.7.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.8.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.9.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.10.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.11.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.12.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.13.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.14.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.15.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.16.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.17.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.18.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.19.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.20.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.21.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.22.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.23.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.24.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.25.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.26.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.27.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.28.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.29.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.30.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.31.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.32.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.33.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.34.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.35.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.36.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.37.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.38.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.39.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.40.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.41.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.42.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.43.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.44.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.45.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.46.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.47.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.48.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.49.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.50.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.51.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.52.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.53.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.54.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.55.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.56.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.57.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.58.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.59.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.60.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.61.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.62.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.63.mlp.experts.63.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.0.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.1.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.2.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.3.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.4.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.5.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.6.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.7.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.8.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.9.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.10.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.11.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.12.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.13.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.14.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.15.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.16.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.17.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.18.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.19.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.20.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.21.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.22.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.23.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.24.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.25.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.26.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.27.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.28.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.29.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.30.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.31.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.32.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.33.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.34.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.35.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.36.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.37.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.38.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.39.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.40.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.41.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.42.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.43.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.44.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.45.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.46.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.47.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.48.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.49.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.50.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.51.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.52.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.53.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.54.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.55.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.56.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.57.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.58.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.59.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.60.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.61.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.62.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.64.mlp.experts.63.down_proj.weight": "model-00078-of-00136.safetensors", - "model.layers.65.mlp.experts.0.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.1.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.2.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.3.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.4.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.5.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.6.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.7.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.8.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.9.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.10.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.11.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.12.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.13.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.14.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.15.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.16.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.17.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.18.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.19.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.20.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.21.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.22.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.23.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.24.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.25.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.26.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.27.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.28.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.29.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.30.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.31.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.32.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.33.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.34.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.35.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.36.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.37.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.38.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.39.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.40.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.41.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.42.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.43.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.44.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.45.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.46.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.47.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.48.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.49.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.50.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.51.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.52.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.53.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.54.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.55.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.56.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.57.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.58.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.59.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.60.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.61.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.62.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.65.mlp.experts.63.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.0.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.1.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.2.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.3.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.4.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.5.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.6.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.7.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.8.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.9.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.10.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.11.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.12.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.13.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.14.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.15.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.16.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.17.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.18.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.19.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.20.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.21.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.22.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.23.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.24.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.25.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.26.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.27.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.28.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.29.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.30.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.31.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.32.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.33.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.34.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.35.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.36.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.37.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.38.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.39.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.40.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.41.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.42.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.43.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.44.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.45.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.46.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.47.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.48.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.49.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.50.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.51.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.52.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.53.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.54.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.55.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.56.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.57.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.58.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.59.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.60.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.61.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.62.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.66.mlp.experts.63.down_proj.weight": "model-00079-of-00136.safetensors", - "model.layers.67.mlp.experts.0.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.1.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.2.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.3.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.4.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.5.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.6.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.7.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.8.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.9.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.10.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.11.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.12.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.13.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.14.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.15.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.16.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.17.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.18.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.19.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.20.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.21.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.22.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.23.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.24.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.25.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.26.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.27.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.28.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.29.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.30.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.31.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.32.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.33.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.34.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.35.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.36.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.37.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.38.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.39.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.40.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.41.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.42.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.43.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.44.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.45.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.46.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.47.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.48.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.49.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.50.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.51.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.52.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.53.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.54.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.55.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.56.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.57.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.58.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.59.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.60.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.61.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.62.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.67.mlp.experts.63.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.0.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.1.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.2.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.3.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.4.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.5.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.6.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.7.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.8.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.9.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.10.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.11.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.12.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.13.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.14.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.15.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.16.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.17.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.18.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.19.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.20.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.21.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.22.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.23.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.24.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.25.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.26.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.27.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.28.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.29.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.30.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.31.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.32.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.33.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.34.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.35.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.36.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.37.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.38.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.39.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.40.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.41.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.42.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.43.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.44.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.45.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.46.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.47.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.48.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.49.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.50.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.51.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.52.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.53.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.54.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.55.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.56.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.57.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.58.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.59.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.60.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.61.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.62.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.68.mlp.experts.63.down_proj.weight": "model-00080-of-00136.safetensors", - "model.layers.69.mlp.experts.0.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.1.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.2.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.3.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.4.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.5.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.6.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.7.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.8.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.9.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.10.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.11.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.12.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.13.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.14.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.15.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.16.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.17.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.18.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.19.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.20.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.21.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.22.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.23.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.24.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.25.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.26.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.27.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.28.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.29.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.30.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.31.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.32.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.33.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.34.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.35.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.36.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.37.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.38.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.39.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.40.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.41.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.42.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.43.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.44.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.45.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.46.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.47.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.48.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.49.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.50.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.51.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.52.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.53.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.54.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.55.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.56.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.57.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.58.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.59.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.60.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.61.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.62.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.69.mlp.experts.63.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.0.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.1.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.2.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.3.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.4.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.5.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.6.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.7.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.8.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.9.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.10.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.11.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.12.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.13.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.14.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.15.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.16.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.17.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.18.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.19.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.20.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.21.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.22.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.23.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.24.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.25.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.26.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.27.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.28.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.29.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.30.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.31.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.32.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.33.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.34.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.35.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.36.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.37.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.38.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.39.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.40.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.41.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.42.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.43.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.44.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.45.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.46.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.47.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.48.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.49.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.50.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.51.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.52.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.53.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.54.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.55.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.56.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.57.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.58.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.59.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.60.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.61.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.62.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.70.mlp.experts.63.down_proj.weight": "model-00081-of-00136.safetensors", - "model.layers.71.mlp.experts.0.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.1.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.2.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.3.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.4.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.5.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.6.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.7.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.8.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.9.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.10.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.11.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.12.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.13.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.14.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.15.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.16.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.17.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.18.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.19.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.20.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.21.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.22.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.23.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.24.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.25.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.26.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.27.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.28.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.29.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.30.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.31.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.32.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.33.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.34.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.35.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.36.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.37.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.38.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.39.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.40.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.41.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.42.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.43.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.44.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.45.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.46.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.47.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.48.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.49.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.50.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.51.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.52.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.53.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.54.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.55.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.56.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.57.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.58.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.59.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.60.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.61.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.62.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.71.mlp.experts.63.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.0.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.1.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.2.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.3.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.4.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.5.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.6.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.7.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.8.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.9.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.10.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.11.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.12.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.13.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.14.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.15.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.16.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.17.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.18.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.19.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.20.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.21.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.22.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.23.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.24.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.25.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.26.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.27.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.28.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.29.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.30.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.31.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.32.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.33.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.34.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.35.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.36.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.37.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.38.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.39.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.40.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.41.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.42.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.43.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.44.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.45.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.46.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.47.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.48.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.49.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.50.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.51.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.52.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.53.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.54.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.55.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.56.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.57.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.58.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.59.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.60.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.61.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.62.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.72.mlp.experts.63.down_proj.weight": "model-00082-of-00136.safetensors", - "model.layers.73.mlp.experts.0.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.1.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.2.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.3.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.4.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.5.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.6.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.7.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.8.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.9.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.10.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.11.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.12.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.13.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.14.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.15.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.16.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.17.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.18.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.19.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.20.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.21.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.22.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.23.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.24.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.25.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.26.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.27.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.28.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.29.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.30.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.31.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.32.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.33.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.34.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.35.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.36.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.37.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.38.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.39.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.40.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.41.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.42.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.43.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.44.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.45.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.46.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.47.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.48.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.49.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.50.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.51.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.52.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.53.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.54.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.55.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.56.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.57.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.58.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.59.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.60.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.61.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.62.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.73.mlp.experts.63.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.0.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.1.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.2.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.3.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.4.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.5.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.6.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.7.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.8.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.9.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.10.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.11.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.12.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.13.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.14.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.15.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.16.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.17.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.18.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.19.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.20.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.21.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.22.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.23.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.24.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.25.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.26.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.27.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.28.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.29.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.30.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.31.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.32.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.33.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.34.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.35.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.36.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.37.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.38.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.39.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.40.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.41.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.42.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.43.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.44.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.45.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.46.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.47.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.48.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.49.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.50.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.51.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.52.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.53.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.54.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.55.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.56.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.57.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.58.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.59.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.60.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.61.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.62.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.74.mlp.experts.63.down_proj.weight": "model-00083-of-00136.safetensors", - "model.layers.75.mlp.experts.0.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.1.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.2.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.3.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.4.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.5.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.6.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.7.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.8.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.9.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.10.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.11.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.12.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.13.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.14.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.15.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.16.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.17.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.18.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.19.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.20.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.21.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.22.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.23.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.24.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.25.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.26.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.27.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.28.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.29.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.30.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.31.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.32.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.33.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.34.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.35.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.36.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.37.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.38.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.39.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.40.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.41.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.42.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.43.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.44.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.45.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.46.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.47.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.48.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.49.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.50.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.51.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.52.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.53.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.54.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.55.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.56.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.57.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.58.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.59.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.60.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.61.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.62.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.75.mlp.experts.63.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.0.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.1.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.2.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.3.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.4.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.5.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.6.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.7.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.8.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.9.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.10.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.11.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.12.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.13.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.14.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.15.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.16.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.17.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.18.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.19.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.20.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.21.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.22.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.23.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.24.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.25.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.26.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.27.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.28.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.29.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.30.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.31.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.32.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.33.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.34.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.35.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.36.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.37.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.38.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.39.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.40.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.41.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.42.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.43.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.44.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.45.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.46.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.47.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.48.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.49.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.50.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.51.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.52.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.53.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.54.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.55.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.56.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.57.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.58.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.59.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.60.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.61.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.62.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.76.mlp.experts.63.down_proj.weight": "model-00084-of-00136.safetensors", - "model.layers.77.mlp.experts.0.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.1.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.2.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.3.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.4.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.5.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.6.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.7.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.8.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.9.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.10.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.11.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.12.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.13.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.14.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.15.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.16.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.17.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.18.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.19.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.20.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.21.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.22.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.23.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.24.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.25.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.26.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.27.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.28.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.29.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.30.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.31.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.32.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.33.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.34.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.35.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.36.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.37.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.38.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.39.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.40.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.41.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.42.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.43.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.44.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.45.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.46.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.47.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.48.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.49.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.50.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.51.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.52.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.53.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.54.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.55.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.56.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.57.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.58.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.59.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.60.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.61.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.62.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.77.mlp.experts.63.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.0.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.1.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.2.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.3.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.4.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.5.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.6.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.7.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.8.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.9.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.10.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.11.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.12.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.13.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.14.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.15.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.16.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.17.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.18.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.19.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.20.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.21.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.22.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.23.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.24.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.25.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.26.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.27.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.28.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.29.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.30.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.31.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.32.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.33.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.34.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.35.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.36.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.37.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.38.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.39.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.40.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.41.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.42.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.43.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.44.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.45.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.46.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.47.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.48.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.49.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.50.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.51.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.52.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.53.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.54.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.55.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.56.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.57.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.58.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.59.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.60.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.61.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.62.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.78.mlp.experts.63.down_proj.weight": "model-00085-of-00136.safetensors", - "model.layers.79.mlp.experts.0.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.1.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.2.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.3.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.4.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.5.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.6.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.7.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.8.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.9.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.10.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.11.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.12.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.13.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.14.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.15.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.16.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.17.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.18.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.19.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.20.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.21.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.22.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.23.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.24.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.25.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.26.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.27.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.28.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.29.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.30.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.31.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.32.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.33.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.34.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.35.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.36.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.37.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.38.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.39.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.40.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.41.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.42.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.43.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.44.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.45.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.46.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.47.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.48.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.49.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.50.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.51.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.52.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.53.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.54.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.55.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.56.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.57.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.58.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.59.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.60.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.61.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.62.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.79.mlp.experts.63.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.0.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.1.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.2.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.3.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.4.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.5.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.6.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.7.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.8.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.9.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.10.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.11.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.12.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.13.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.14.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.15.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.16.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.17.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.18.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.19.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.20.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.21.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.22.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.23.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.24.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.25.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.26.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.27.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.28.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.29.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.30.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.31.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.32.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.33.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.34.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.35.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.36.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.37.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.38.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.39.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.40.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.41.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.42.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.43.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.44.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.45.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.46.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.47.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.48.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.49.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.50.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.51.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.52.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.53.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.54.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.55.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.56.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.57.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.58.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.59.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.60.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.61.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.62.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.80.mlp.experts.63.down_proj.weight": "model-00086-of-00136.safetensors", - "model.layers.81.mlp.experts.0.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.1.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.2.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.3.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.4.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.5.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.6.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.7.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.8.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.9.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.10.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.11.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.12.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.13.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.14.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.15.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.16.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.17.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.18.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.19.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.20.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.21.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.22.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.23.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.24.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.25.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.26.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.27.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.28.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.29.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.30.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.31.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.32.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.33.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.34.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.35.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.36.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.37.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.38.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.39.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.40.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.41.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.42.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.43.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.44.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.45.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.46.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.47.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.48.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.49.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.50.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.51.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.52.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.53.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.54.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.55.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.56.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.57.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.58.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.59.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.60.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.61.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.62.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.81.mlp.experts.63.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.0.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.1.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.2.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.3.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.4.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.5.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.6.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.7.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.8.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.9.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.10.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.11.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.12.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.13.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.14.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.15.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.16.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.17.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.18.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.19.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.20.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.21.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.22.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.23.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.24.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.25.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.26.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.27.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.28.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.29.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.30.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.31.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.32.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.33.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.34.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.35.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.36.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.37.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.38.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.39.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.40.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.41.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.42.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.43.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.44.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.45.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.46.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.47.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.48.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.49.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.50.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.51.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.52.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.53.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.54.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.55.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.56.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.57.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.58.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.59.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.60.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.61.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.62.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.82.mlp.experts.63.down_proj.weight": "model-00087-of-00136.safetensors", - "model.layers.83.mlp.experts.0.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.1.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.2.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.3.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.4.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.5.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.6.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.7.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.8.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.9.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.10.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.11.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.12.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.13.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.14.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.15.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.16.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.17.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.18.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.19.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.20.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.21.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.22.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.23.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.24.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.25.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.26.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.27.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.28.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.29.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.30.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.31.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.32.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.33.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.34.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.35.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.36.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.37.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.38.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.39.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.40.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.41.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.42.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.43.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.44.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.45.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.46.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.47.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.48.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.49.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.50.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.51.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.52.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.53.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.54.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.55.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.56.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.57.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.58.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.59.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.60.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.61.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.62.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.83.mlp.experts.63.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.0.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.1.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.2.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.3.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.4.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.5.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.6.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.7.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.8.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.9.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.10.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.11.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.12.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.13.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.14.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.15.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.16.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.17.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.18.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.19.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.20.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.21.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.22.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.23.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.24.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.25.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.26.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.27.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.28.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.29.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.30.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.31.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.32.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.33.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.34.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.35.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.36.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.37.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.38.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.39.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.40.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.41.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.42.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.43.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.44.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.45.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.46.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.47.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.48.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.49.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.50.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.51.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.52.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.53.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.54.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.55.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.56.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.57.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.58.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.59.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.60.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.61.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.62.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.84.mlp.experts.63.down_proj.weight": "model-00088-of-00136.safetensors", - "model.layers.85.mlp.experts.0.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.1.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.2.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.3.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.4.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.5.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.6.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.7.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.8.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.9.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.10.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.11.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.12.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.13.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.14.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.15.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.16.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.17.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.18.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.19.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.20.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.21.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.22.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.23.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.24.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.25.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.26.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.27.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.28.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.29.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.30.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.31.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.32.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.33.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.34.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.35.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.36.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.37.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.38.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.39.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.40.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.41.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.42.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.43.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.44.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.45.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.46.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.47.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.48.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.49.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.50.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.51.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.52.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.53.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.54.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.55.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.56.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.57.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.58.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.59.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.60.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.61.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.62.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.85.mlp.experts.63.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.0.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.1.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.2.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.3.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.4.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.5.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.6.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.7.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.8.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.9.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.10.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.11.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.12.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.13.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.14.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.15.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.16.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.17.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.18.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.19.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.20.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.21.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.22.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.23.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.24.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.25.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.26.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.27.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.28.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.29.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.30.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.31.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.32.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.33.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.34.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.35.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.36.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.37.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.38.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.39.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.40.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.41.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.42.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.43.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.44.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.45.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.46.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.47.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.48.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.49.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.50.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.51.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.52.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.53.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.54.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.55.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.56.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.57.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.58.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.59.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.60.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.61.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.62.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.86.mlp.experts.63.down_proj.weight": "model-00089-of-00136.safetensors", - "model.layers.87.mlp.experts.0.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.1.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.2.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.3.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.4.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.5.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.6.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.7.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.8.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.9.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.10.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.11.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.12.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.13.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.14.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.15.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.16.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.17.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.18.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.19.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.20.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.21.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.22.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.23.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.24.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.25.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.26.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.27.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.28.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.29.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.30.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.31.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.32.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.33.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.34.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.35.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.36.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.37.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.38.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.39.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.40.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.41.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.42.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.43.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.44.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.45.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.46.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.47.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.48.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.49.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.50.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.51.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.52.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.53.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.54.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.55.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.56.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.57.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.58.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.59.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.60.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.61.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.62.down_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.experts.63.down_proj.weight": "model-00090-of-00136.safetensors", - "model.norm.weight": "model-00090-of-00136.safetensors", - "lm_head.weight": "model-00090-of-00136.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.0.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.1.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.2.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.3.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.4.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.5.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.6.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.7.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.8.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.9.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.10.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.11.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.12.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.13.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.14.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.15.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.16.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.17.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.18.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.19.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.20.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.21.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.22.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.23.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.24.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.25.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.26.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.27.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.28.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.29.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.30.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.31.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.32.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.32.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.33.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.33.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.34.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.34.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.35.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.35.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.36.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.36.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.37.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.37.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.38.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.38.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.39.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.39.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.40.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.40.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.41.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.41.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.42.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.42.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.43.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.43.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.44.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.44.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.45.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.45.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.46.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.46.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.47.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.47.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.48.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.48.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.49.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.49.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.50.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.50.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.51.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.51.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.52.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.52.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.53.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.53.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.54.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.54.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.55.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.55.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.56.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.56.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.57.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.57.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.58.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.58.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.59.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.59.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.60.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.60.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.61.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.61.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.62.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.62.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.63.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.63.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.64.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.64.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.65.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.65.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.66.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.66.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.67.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.67.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.68.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.68.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.69.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.69.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.70.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.70.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.71.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.71.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.72.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.72.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.73.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.73.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.74.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.74.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.75.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.75.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.76.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.76.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.77.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.77.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.78.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.78.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.79.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.79.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.80.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.80.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.81.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.81.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.82.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.82.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.83.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.83.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.84.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.84.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.85.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.85.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.86.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.86.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.87.post_attention_layernorm.weight": "model-00090-of-00136.safetensors", - "model.layers.87.mlp.gate.weight": "model-00090-of-00136.safetensors", - "model.layers.0.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00090-of-00136.safetensors", - "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.62.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.63.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.64.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.65.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.66.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.67.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.68.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.69.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.70.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.71.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.72.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.73.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.74.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.75.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.76.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.77.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.78.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.79.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.80.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.81.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.82.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.83.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.84.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.85.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.86.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.87.mlp.shared_experts.gate_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.0.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.1.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.2.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.3.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.4.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.5.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.6.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.7.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.8.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.9.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.10.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.11.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.12.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.13.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.14.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.15.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.16.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.17.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.18.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.19.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.20.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.21.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.22.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.23.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.24.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.25.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.26.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.27.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.28.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.29.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.30.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.31.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.32.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.33.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.34.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.35.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.36.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.37.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.38.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.39.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.40.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.41.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.42.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.43.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.44.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.45.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.46.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.47.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.48.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.49.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.50.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.51.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.52.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.53.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.54.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.55.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.56.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.57.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.58.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.59.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.60.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.61.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.62.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.0.mlp.experts.63.up_proj.weight": "model-00091-of-00136.safetensors", - "model.layers.1.mlp.experts.0.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.1.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.2.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.3.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.4.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.5.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.6.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.7.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.8.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.9.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.10.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.11.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.12.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.13.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.14.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.15.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.16.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.17.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.18.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.19.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.20.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.21.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.22.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.23.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.24.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.25.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.26.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.27.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.28.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.29.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.30.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.31.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.32.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.33.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.34.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.35.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.36.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.37.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.38.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.39.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.40.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.41.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.42.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.43.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.44.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.45.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.46.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.47.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.48.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.49.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.50.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.51.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.52.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.53.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.54.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.55.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.56.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.57.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.58.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.59.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.60.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.61.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.62.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.1.mlp.experts.63.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.0.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.1.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.2.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.3.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.4.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.5.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.6.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.7.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.8.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.9.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.10.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.11.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.12.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.13.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.14.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.15.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.16.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.17.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.18.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.19.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.20.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.21.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.22.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.23.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.24.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.25.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.26.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.27.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.28.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.29.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.30.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.31.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.32.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.33.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.34.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.35.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.36.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.37.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.38.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.39.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.40.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.41.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.42.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.43.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.44.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.45.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.46.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.47.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.48.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.49.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.50.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.51.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.52.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.53.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.54.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.55.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.56.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.57.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.58.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.59.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.60.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.61.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.62.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.2.mlp.experts.63.up_proj.weight": "model-00092-of-00136.safetensors", - "model.layers.3.mlp.experts.0.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.1.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.2.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.3.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.4.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.5.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.6.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.7.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.8.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.9.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.10.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.11.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.12.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.13.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.14.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.15.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.16.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.17.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.18.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.19.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.20.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.21.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.22.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.23.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.24.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.25.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.26.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.27.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.28.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.29.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.30.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.31.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.32.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.33.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.34.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.35.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.36.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.37.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.38.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.39.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.40.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.41.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.42.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.43.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.44.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.45.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.46.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.47.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.48.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.49.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.50.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.51.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.52.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.53.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.54.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.55.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.56.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.57.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.58.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.59.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.60.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.61.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.62.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.3.mlp.experts.63.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.0.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.1.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.2.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.3.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.4.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.5.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.6.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.7.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.8.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.9.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.10.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.11.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.12.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.13.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.14.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.15.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.16.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.17.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.18.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.19.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.20.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.21.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.22.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.23.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.24.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.25.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.26.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.27.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.28.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.29.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.30.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.31.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.32.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.33.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.34.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.35.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.36.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.37.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.38.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.39.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.40.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.41.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.42.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.43.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.44.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.45.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.46.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.47.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.48.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.49.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.50.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.51.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.52.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.53.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.54.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.55.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.56.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.57.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.58.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.59.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.60.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.61.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.62.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.4.mlp.experts.63.up_proj.weight": "model-00093-of-00136.safetensors", - "model.layers.5.mlp.experts.0.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.1.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.2.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.3.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.4.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.5.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.6.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.7.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.8.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.9.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.10.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.11.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.12.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.13.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.14.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.15.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.16.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.17.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.18.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.19.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.20.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.21.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.22.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.23.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.24.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.25.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.26.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.27.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.28.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.29.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.30.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.31.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.32.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.33.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.34.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.35.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.36.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.37.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.38.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.39.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.40.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.41.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.42.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.43.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.44.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.45.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.46.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.47.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.48.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.49.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.50.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.51.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.52.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.53.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.54.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.55.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.56.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.57.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.58.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.59.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.60.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.61.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.62.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.5.mlp.experts.63.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.0.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.1.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.2.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.3.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.4.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.5.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.6.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.7.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.8.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.9.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.10.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.11.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.12.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.13.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.14.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.15.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.16.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.17.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.18.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.19.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.20.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.21.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.22.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.23.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.24.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.25.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.26.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.27.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.28.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.29.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.30.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.31.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.32.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.33.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.34.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.35.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.36.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.37.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.38.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.39.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.40.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.41.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.42.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.43.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.44.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.45.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.46.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.47.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.48.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.49.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.50.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.51.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.52.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.53.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.54.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.55.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.56.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.57.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.58.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.59.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.60.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.61.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.62.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.6.mlp.experts.63.up_proj.weight": "model-00094-of-00136.safetensors", - "model.layers.7.mlp.experts.0.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.1.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.2.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.3.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.4.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.5.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.6.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.7.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.8.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.9.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.10.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.11.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.12.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.13.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.14.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.15.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.16.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.17.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.18.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.19.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.20.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.21.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.22.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.23.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.24.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.25.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.26.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.27.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.28.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.29.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.30.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.31.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.32.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.33.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.34.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.35.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.36.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.37.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.38.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.39.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.40.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.41.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.42.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.43.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.44.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.45.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.46.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.47.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.48.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.49.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.50.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.51.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.52.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.53.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.54.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.55.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.56.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.57.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.58.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.59.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.60.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.61.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.62.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.7.mlp.experts.63.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.0.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.1.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.2.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.3.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.4.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.5.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.6.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.7.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.8.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.9.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.10.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.11.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.12.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.13.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.14.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.15.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.16.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.17.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.18.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.19.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.20.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.21.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.22.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.23.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.24.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.25.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.26.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.27.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.28.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.29.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.30.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.31.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.32.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.33.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.34.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.35.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.36.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.37.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.38.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.39.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.40.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.41.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.42.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.43.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.44.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.45.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.46.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.47.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.48.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.49.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.50.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.51.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.52.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.53.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.54.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.55.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.56.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.57.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.58.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.59.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.60.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.61.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.62.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.8.mlp.experts.63.up_proj.weight": "model-00095-of-00136.safetensors", - "model.layers.9.mlp.experts.0.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.1.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.2.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.3.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.4.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.5.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.6.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.7.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.8.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.9.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.10.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.11.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.12.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.13.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.14.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.15.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.16.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.17.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.18.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.19.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.20.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.21.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.22.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.23.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.24.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.25.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.26.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.27.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.28.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.29.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.30.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.31.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.32.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.33.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.34.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.35.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.36.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.37.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.38.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.39.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.40.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.41.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.42.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.43.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.44.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.45.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.46.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.47.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.48.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.49.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.50.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.51.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.52.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.53.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.54.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.55.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.56.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.57.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.58.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.59.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.60.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.61.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.62.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.9.mlp.experts.63.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.0.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.1.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.2.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.3.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.4.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.5.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.6.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.7.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.8.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.9.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.10.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.11.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.12.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.13.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.14.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.15.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.16.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.17.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.18.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.19.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.20.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.21.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.22.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.23.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.24.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.25.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.26.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.27.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.28.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.29.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.30.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.31.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.32.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.33.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.34.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.35.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.36.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.37.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.38.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.39.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.40.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.41.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.42.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.43.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.44.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.45.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.46.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.47.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.48.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.49.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.50.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.51.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.52.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.53.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.54.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.55.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.56.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.57.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.58.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.59.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.60.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.61.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.62.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.10.mlp.experts.63.up_proj.weight": "model-00096-of-00136.safetensors", - "model.layers.11.mlp.experts.0.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.1.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.2.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.3.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.4.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.5.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.6.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.7.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.8.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.9.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.10.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.11.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.12.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.13.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.14.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.15.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.16.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.17.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.18.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.19.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.20.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.21.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.22.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.23.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.24.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.25.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.26.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.27.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.28.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.29.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.30.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.31.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.32.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.33.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.34.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.35.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.36.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.37.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.38.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.39.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.40.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.41.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.42.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.43.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.44.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.45.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.46.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.47.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.48.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.49.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.50.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.51.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.52.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.53.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.54.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.55.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.56.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.57.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.58.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.59.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.60.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.61.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.62.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.11.mlp.experts.63.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.0.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.1.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.2.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.3.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.4.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.5.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.6.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.7.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.8.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.9.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.10.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.11.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.12.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.13.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.14.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.15.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.16.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.17.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.18.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.19.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.20.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.21.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.22.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.23.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.24.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.25.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.26.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.27.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.28.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.29.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.30.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.31.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.32.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.33.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.34.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.35.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.36.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.37.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.38.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.39.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.40.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.41.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.42.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.43.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.44.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.45.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.46.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.47.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.48.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.49.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.50.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.51.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.52.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.53.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.54.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.55.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.56.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.57.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.58.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.59.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.60.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.61.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.62.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.12.mlp.experts.63.up_proj.weight": "model-00097-of-00136.safetensors", - "model.layers.13.mlp.experts.0.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.1.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.2.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.3.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.4.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.5.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.6.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.7.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.8.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.9.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.10.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.11.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.12.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.13.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.14.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.15.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.16.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.17.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.18.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.19.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.20.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.21.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.22.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.23.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.24.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.25.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.26.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.27.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.28.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.29.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.30.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.31.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.32.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.33.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.34.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.35.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.36.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.37.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.38.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.39.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.40.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.41.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.42.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.43.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.44.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.45.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.46.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.47.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.48.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.49.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.50.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.51.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.52.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.53.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.54.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.55.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.56.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.57.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.58.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.59.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.60.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.61.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.62.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.13.mlp.experts.63.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.0.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.1.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.2.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.3.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.4.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.5.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.6.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.7.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.8.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.9.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.10.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.11.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.12.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.13.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.14.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.15.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.16.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.17.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.18.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.19.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.20.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.21.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.22.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.23.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.24.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.25.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.26.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.27.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.28.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.29.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.30.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.31.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.32.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.33.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.34.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.35.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.36.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.37.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.38.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.39.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.40.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.41.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.42.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.43.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.44.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.45.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.46.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.47.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.48.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.49.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.50.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.51.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.52.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.53.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.54.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.55.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.56.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.57.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.58.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.59.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.60.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.61.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.62.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.14.mlp.experts.63.up_proj.weight": "model-00098-of-00136.safetensors", - "model.layers.15.mlp.experts.0.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.1.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.2.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.3.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.4.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.5.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.6.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.7.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.8.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.9.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.10.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.11.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.12.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.13.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.14.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.15.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.16.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.17.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.18.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.19.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.20.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.21.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.22.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.23.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.24.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.25.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.26.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.27.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.28.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.29.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.30.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.31.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.32.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.33.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.34.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.35.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.36.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.37.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.38.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.39.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.40.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.41.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.42.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.43.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.44.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.45.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.46.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.47.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.48.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.49.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.50.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.51.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.52.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.53.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.54.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.55.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.56.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.57.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.58.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.59.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.60.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.61.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.62.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.15.mlp.experts.63.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.0.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.1.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.2.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.3.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.4.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.5.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.6.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.7.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.8.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.9.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.10.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.11.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.12.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.13.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.14.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.15.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.16.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.17.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.18.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.19.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.20.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.21.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.22.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.23.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.24.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.25.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.26.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.27.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.28.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.29.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.30.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.31.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.32.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.33.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.34.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.35.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.36.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.37.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.38.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.39.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.40.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.41.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.42.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.43.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.44.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.45.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.46.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.47.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.48.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.49.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.50.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.51.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.52.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.53.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.54.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.55.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.56.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.57.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.58.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.59.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.60.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.61.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.62.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.16.mlp.experts.63.up_proj.weight": "model-00099-of-00136.safetensors", - "model.layers.17.mlp.experts.0.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.1.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.2.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.3.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.4.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.5.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.6.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.7.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.8.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.9.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.10.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.11.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.12.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.13.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.14.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.15.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.16.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.17.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.18.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.19.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.20.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.21.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.22.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.23.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.24.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.25.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.26.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.27.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.28.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.29.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.30.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.31.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.32.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.33.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.34.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.35.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.36.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.37.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.38.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.39.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.40.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.41.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.42.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.43.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.44.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.45.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.46.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.47.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.48.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.49.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.50.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.51.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.52.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.53.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.54.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.55.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.56.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.57.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.58.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.59.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.60.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.61.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.62.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.17.mlp.experts.63.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.0.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.1.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.2.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.3.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.4.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.5.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.6.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.7.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.8.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.9.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.10.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.11.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.12.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.13.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.14.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.15.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.16.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.17.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.18.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.19.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.20.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.21.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.22.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.23.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.24.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.25.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.26.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.27.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.28.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.29.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.30.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.31.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.32.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.33.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.34.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.35.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.36.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.37.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.38.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.39.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.40.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.41.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.42.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.43.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.44.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.45.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.46.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.47.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.48.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.49.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.50.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.51.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.52.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.53.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.54.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.55.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.56.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.57.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.58.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.59.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.60.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.61.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.62.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.18.mlp.experts.63.up_proj.weight": "model-00100-of-00136.safetensors", - "model.layers.19.mlp.experts.0.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.1.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.2.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.3.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.4.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.5.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.6.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.7.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.8.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.9.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.10.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.11.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.12.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.13.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.14.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.15.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.16.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.17.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.18.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.19.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.20.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.21.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.22.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.23.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.24.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.25.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.26.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.27.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.28.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.29.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.30.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.31.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.32.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.33.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.34.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.35.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.36.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.37.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.38.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.39.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.40.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.41.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.42.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.43.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.44.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.45.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.46.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.47.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.48.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.49.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.50.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.51.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.52.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.53.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.54.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.55.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.56.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.57.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.58.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.59.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.60.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.61.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.62.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.19.mlp.experts.63.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.0.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.1.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.2.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.3.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.4.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.5.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.6.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.7.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.8.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.9.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.10.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.11.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.12.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.13.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.14.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.15.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.16.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.17.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.18.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.19.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.20.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.21.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.22.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.23.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.24.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.25.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.26.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.27.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.28.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.29.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.30.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.31.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.32.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.33.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.34.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.35.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.36.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.37.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.38.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.39.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.40.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.41.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.42.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.43.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.44.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.45.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.46.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.47.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.48.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.49.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.50.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.51.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.52.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.53.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.54.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.55.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.56.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.57.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.58.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.59.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.60.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.61.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.62.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.20.mlp.experts.63.up_proj.weight": "model-00101-of-00136.safetensors", - "model.layers.21.mlp.experts.0.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.1.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.2.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.3.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.4.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.5.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.6.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.7.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.8.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.9.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.10.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.11.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.12.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.13.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.14.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.15.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.16.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.17.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.18.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.19.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.20.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.21.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.22.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.23.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.24.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.25.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.26.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.27.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.28.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.29.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.30.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.31.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.32.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.33.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.34.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.35.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.36.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.37.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.38.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.39.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.40.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.41.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.42.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.43.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.44.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.45.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.46.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.47.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.48.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.49.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.50.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.51.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.52.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.53.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.54.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.55.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.56.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.57.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.58.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.59.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.60.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.61.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.62.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.21.mlp.experts.63.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.0.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.1.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.2.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.3.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.4.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.5.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.6.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.7.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.8.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.9.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.10.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.11.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.12.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.13.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.14.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.15.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.16.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.17.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.18.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.19.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.20.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.21.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.22.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.23.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.24.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.25.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.26.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.27.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.28.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.29.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.30.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.31.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.32.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.33.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.34.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.35.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.36.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.37.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.38.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.39.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.40.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.41.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.42.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.43.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.44.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.45.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.46.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.47.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.48.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.49.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.50.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.51.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.52.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.53.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.54.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.55.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.56.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.57.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.58.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.59.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.60.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.61.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.62.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.22.mlp.experts.63.up_proj.weight": "model-00102-of-00136.safetensors", - "model.layers.23.mlp.experts.0.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.1.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.2.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.3.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.4.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.5.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.6.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.7.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.8.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.9.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.10.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.11.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.12.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.13.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.14.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.15.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.16.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.17.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.18.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.19.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.20.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.21.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.22.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.23.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.24.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.25.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.26.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.27.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.28.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.29.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.30.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.31.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.32.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.33.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.34.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.35.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.36.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.37.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.38.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.39.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.40.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.41.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.42.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.43.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.44.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.45.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.46.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.47.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.48.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.49.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.50.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.51.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.52.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.53.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.54.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.55.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.56.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.57.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.58.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.59.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.60.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.61.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.62.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.23.mlp.experts.63.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.0.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.1.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.2.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.3.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.4.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.5.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.6.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.7.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.8.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.9.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.10.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.11.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.12.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.13.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.14.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.15.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.16.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.17.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.18.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.19.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.20.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.21.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.22.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.23.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.24.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.25.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.26.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.27.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.28.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.29.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.30.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.31.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.32.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.33.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.34.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.35.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.36.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.37.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.38.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.39.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.40.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.41.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.42.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.43.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.44.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.45.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.46.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.47.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.48.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.49.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.50.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.51.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.52.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.53.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.54.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.55.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.56.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.57.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.58.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.59.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.60.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.61.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.62.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.24.mlp.experts.63.up_proj.weight": "model-00103-of-00136.safetensors", - "model.layers.25.mlp.experts.0.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.1.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.2.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.3.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.4.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.5.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.6.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.7.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.8.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.9.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.10.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.11.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.12.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.13.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.14.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.15.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.16.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.17.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.18.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.19.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.20.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.21.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.22.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.23.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.24.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.25.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.26.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.27.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.28.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.29.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.30.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.31.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.32.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.33.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.34.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.35.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.36.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.37.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.38.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.39.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.40.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.41.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.42.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.43.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.44.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.45.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.46.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.47.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.48.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.49.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.50.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.51.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.52.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.53.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.54.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.55.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.56.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.57.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.58.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.59.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.60.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.61.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.62.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.25.mlp.experts.63.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.0.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.1.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.2.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.3.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.4.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.5.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.6.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.7.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.8.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.9.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.10.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.11.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.12.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.13.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.14.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.15.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.16.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.17.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.18.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.19.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.20.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.21.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.22.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.23.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.24.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.25.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.26.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.27.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.28.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.29.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.30.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.31.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.32.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.33.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.34.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.35.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.36.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.37.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.38.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.39.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.40.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.41.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.42.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.43.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.44.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.45.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.46.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.47.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.48.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.49.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.50.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.51.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.52.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.53.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.54.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.55.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.56.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.57.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.58.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.59.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.60.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.61.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.62.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.26.mlp.experts.63.up_proj.weight": "model-00104-of-00136.safetensors", - "model.layers.27.mlp.experts.0.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.1.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.2.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.3.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.4.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.5.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.6.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.7.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.8.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.9.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.10.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.11.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.12.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.13.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.14.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.15.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.16.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.17.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.18.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.19.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.20.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.21.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.22.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.23.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.24.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.25.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.26.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.27.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.28.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.29.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.30.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.31.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.32.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.33.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.34.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.35.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.36.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.37.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.38.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.39.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.40.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.41.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.42.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.43.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.44.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.45.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.46.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.47.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.48.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.49.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.50.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.51.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.52.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.53.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.54.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.55.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.56.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.57.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.58.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.59.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.60.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.61.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.62.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.27.mlp.experts.63.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.0.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.1.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.2.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.3.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.4.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.5.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.6.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.7.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.8.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.9.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.10.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.11.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.12.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.13.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.14.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.15.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.16.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.17.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.18.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.19.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.20.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.21.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.22.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.23.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.24.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.25.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.26.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.27.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.28.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.29.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.30.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.31.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.32.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.33.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.34.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.35.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.36.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.37.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.38.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.39.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.40.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.41.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.42.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.43.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.44.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.45.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.46.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.47.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.48.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.49.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.50.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.51.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.52.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.53.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.54.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.55.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.56.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.57.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.58.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.59.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.60.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.61.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.62.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.28.mlp.experts.63.up_proj.weight": "model-00105-of-00136.safetensors", - "model.layers.29.mlp.experts.0.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.1.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.2.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.3.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.4.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.5.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.6.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.7.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.8.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.9.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.10.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.11.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.12.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.13.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.14.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.15.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.16.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.17.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.18.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.19.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.20.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.21.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.22.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.23.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.24.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.25.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.26.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.27.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.28.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.29.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.30.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.31.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.32.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.33.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.34.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.35.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.36.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.37.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.38.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.39.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.40.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.41.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.42.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.43.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.44.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.45.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.46.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.47.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.48.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.49.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.50.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.51.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.52.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.53.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.54.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.55.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.56.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.57.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.58.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.59.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.60.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.61.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.62.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.29.mlp.experts.63.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.0.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.1.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.2.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.3.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.4.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.5.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.6.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.7.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.8.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.9.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.10.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.11.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.12.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.13.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.14.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.15.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.16.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.17.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.18.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.19.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.20.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.21.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.22.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.23.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.24.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.25.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.26.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.27.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.28.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.29.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.30.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.31.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.32.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.33.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.34.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.35.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.36.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.37.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.38.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.39.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.40.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.41.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.42.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.43.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.44.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.45.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.46.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.47.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.48.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.49.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.50.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.51.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.52.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.53.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.54.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.55.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.56.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.57.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.58.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.59.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.60.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.61.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.62.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.30.mlp.experts.63.up_proj.weight": "model-00106-of-00136.safetensors", - "model.layers.31.mlp.experts.0.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.1.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.2.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.3.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.4.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.5.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.6.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.7.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.8.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.9.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.10.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.11.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.12.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.13.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.14.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.15.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.16.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.17.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.18.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.19.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.20.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.21.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.22.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.23.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.24.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.25.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.26.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.27.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.28.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.29.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.30.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.31.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.32.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.33.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.34.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.35.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.36.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.37.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.38.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.39.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.40.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.41.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.42.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.43.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.44.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.45.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.46.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.47.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.48.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.49.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.50.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.51.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.52.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.53.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.54.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.55.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.56.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.57.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.58.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.59.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.60.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.61.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.62.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.31.mlp.experts.63.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.0.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.1.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.2.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.3.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.4.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.5.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.6.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.7.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.8.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.9.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.10.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.11.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.12.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.13.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.14.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.15.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.16.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.17.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.18.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.19.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.20.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.21.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.22.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.23.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.24.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.25.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.26.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.27.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.28.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.29.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.30.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.31.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.32.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.33.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.34.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.35.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.36.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.37.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.38.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.39.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.40.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.41.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.42.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.43.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.44.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.45.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.46.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.47.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.48.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.49.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.50.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.51.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.52.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.53.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.54.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.55.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.56.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.57.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.58.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.59.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.60.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.61.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.62.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.32.mlp.experts.63.up_proj.weight": "model-00107-of-00136.safetensors", - "model.layers.33.mlp.experts.0.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.1.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.2.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.3.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.4.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.5.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.6.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.7.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.8.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.9.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.10.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.11.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.12.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.13.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.14.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.15.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.16.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.17.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.18.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.19.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.20.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.21.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.22.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.23.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.24.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.25.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.26.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.27.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.28.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.29.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.30.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.31.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.32.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.33.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.34.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.35.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.36.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.37.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.38.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.39.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.40.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.41.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.42.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.43.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.44.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.45.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.46.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.47.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.48.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.49.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.50.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.51.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.52.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.53.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.54.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.55.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.56.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.57.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.58.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.59.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.60.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.61.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.62.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.33.mlp.experts.63.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.0.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.1.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.2.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.3.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.4.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.5.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.6.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.7.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.8.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.9.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.10.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.11.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.12.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.13.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.14.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.15.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.16.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.17.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.18.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.19.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.20.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.21.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.22.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.23.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.24.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.25.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.26.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.27.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.28.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.29.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.30.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.31.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.32.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.33.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.34.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.35.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.36.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.37.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.38.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.39.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.40.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.41.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.42.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.43.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.44.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.45.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.46.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.47.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.48.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.49.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.50.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.51.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.52.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.53.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.54.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.55.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.56.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.57.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.58.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.59.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.60.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.61.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.62.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.34.mlp.experts.63.up_proj.weight": "model-00108-of-00136.safetensors", - "model.layers.35.mlp.experts.0.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.1.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.2.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.3.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.4.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.5.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.6.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.7.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.8.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.9.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.10.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.11.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.12.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.13.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.14.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.15.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.16.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.17.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.18.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.19.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.20.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.21.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.22.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.23.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.24.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.25.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.26.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.27.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.28.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.29.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.30.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.31.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.32.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.33.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.34.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.35.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.36.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.37.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.38.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.39.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.40.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.41.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.42.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.43.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.44.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.45.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.46.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.47.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.48.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.49.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.50.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.51.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.52.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.53.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.54.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.55.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.56.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.57.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.58.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.59.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.60.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.61.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.62.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.35.mlp.experts.63.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.0.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.1.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.2.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.3.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.4.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.5.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.6.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.7.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.8.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.9.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.10.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.11.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.12.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.13.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.14.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.15.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.16.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.17.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.18.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.19.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.20.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.21.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.22.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.23.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.24.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.25.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.26.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.27.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.28.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.29.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.30.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.31.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.32.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.33.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.34.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.35.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.36.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.37.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.38.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.39.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.40.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.41.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.42.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.43.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.44.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.45.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.46.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.47.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.48.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.49.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.50.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.51.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.52.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.53.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.54.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.55.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.56.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.57.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.58.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.59.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.60.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.61.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.62.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.36.mlp.experts.63.up_proj.weight": "model-00109-of-00136.safetensors", - "model.layers.37.mlp.experts.0.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.1.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.2.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.3.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.4.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.5.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.6.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.7.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.8.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.9.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.10.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.11.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.12.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.13.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.14.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.15.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.16.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.17.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.18.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.19.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.20.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.21.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.22.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.23.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.24.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.25.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.26.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.27.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.28.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.29.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.30.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.31.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.32.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.33.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.34.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.35.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.36.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.37.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.38.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.39.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.40.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.41.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.42.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.43.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.44.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.45.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.46.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.47.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.48.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.49.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.50.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.51.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.52.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.53.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.54.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.55.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.56.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.57.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.58.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.59.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.60.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.61.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.62.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.37.mlp.experts.63.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.0.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.1.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.2.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.3.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.4.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.5.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.6.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.7.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.8.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.9.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.10.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.11.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.12.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.13.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.14.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.15.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.16.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.17.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.18.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.19.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.20.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.21.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.22.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.23.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.24.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.25.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.26.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.27.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.28.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.29.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.30.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.31.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.32.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.33.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.34.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.35.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.36.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.37.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.38.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.39.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.40.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.41.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.42.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.43.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.44.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.45.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.46.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.47.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.48.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.49.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.50.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.51.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.52.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.53.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.54.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.55.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.56.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.57.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.58.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.59.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.60.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.61.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.62.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.38.mlp.experts.63.up_proj.weight": "model-00110-of-00136.safetensors", - "model.layers.39.mlp.experts.0.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.1.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.2.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.3.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.4.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.5.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.6.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.7.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.8.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.9.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.10.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.11.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.12.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.13.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.14.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.15.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.16.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.17.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.18.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.19.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.20.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.21.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.22.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.23.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.24.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.25.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.26.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.27.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.28.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.29.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.30.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.31.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.32.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.33.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.34.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.35.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.36.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.37.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.38.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.39.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.40.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.41.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.42.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.43.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.44.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.45.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.46.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.47.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.48.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.49.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.50.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.51.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.52.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.53.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.54.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.55.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.56.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.57.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.58.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.59.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.60.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.61.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.62.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.39.mlp.experts.63.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.0.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.1.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.2.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.3.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.4.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.5.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.6.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.7.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.8.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.9.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.10.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.11.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.12.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.13.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.14.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.15.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.16.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.17.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.18.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.19.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.20.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.21.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.22.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.23.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.24.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.25.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.26.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.27.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.28.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.29.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.30.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.31.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.32.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.33.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.34.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.35.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.36.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.37.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.38.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.39.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.40.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.41.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.42.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.43.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.44.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.45.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.46.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.47.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.48.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.49.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.50.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.51.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.52.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.53.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.54.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.55.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.56.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.57.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.58.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.59.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.60.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.61.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.62.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.40.mlp.experts.63.up_proj.weight": "model-00111-of-00136.safetensors", - "model.layers.41.mlp.experts.0.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.1.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.2.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.3.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.4.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.5.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.6.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.7.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.8.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.9.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.10.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.11.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.12.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.13.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.14.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.15.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.16.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.17.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.18.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.19.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.20.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.21.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.22.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.23.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.24.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.25.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.26.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.27.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.28.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.29.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.30.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.31.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.32.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.33.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.34.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.35.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.36.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.37.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.38.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.39.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.40.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.41.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.42.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.43.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.44.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.45.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.46.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.47.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.48.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.49.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.50.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.51.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.52.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.53.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.54.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.55.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.56.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.57.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.58.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.59.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.60.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.61.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.62.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.41.mlp.experts.63.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.0.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.1.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.2.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.3.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.4.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.5.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.6.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.7.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.8.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.9.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.10.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.11.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.12.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.13.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.14.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.15.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.16.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.17.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.18.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.19.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.20.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.21.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.22.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.23.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.24.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.25.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.26.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.27.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.28.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.29.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.30.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.31.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.32.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.33.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.34.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.35.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.36.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.37.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.38.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.39.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.40.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.41.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.42.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.43.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.44.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.45.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.46.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.47.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.48.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.49.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.50.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.51.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.52.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.53.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.54.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.55.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.56.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.57.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.58.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.59.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.60.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.61.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.62.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.42.mlp.experts.63.up_proj.weight": "model-00112-of-00136.safetensors", - "model.layers.43.mlp.experts.0.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.1.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.2.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.3.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.4.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.5.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.6.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.7.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.8.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.9.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.10.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.11.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.12.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.13.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.14.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.15.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.16.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.17.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.18.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.19.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.20.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.21.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.22.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.23.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.24.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.25.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.26.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.27.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.28.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.29.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.30.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.31.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.32.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.33.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.34.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.35.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.36.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.37.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.38.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.39.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.40.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.41.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.42.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.43.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.44.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.45.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.46.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.47.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.48.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.49.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.50.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.51.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.52.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.53.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.54.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.55.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.56.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.57.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.58.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.59.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.60.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.61.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.62.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.43.mlp.experts.63.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.0.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.1.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.2.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.3.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.4.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.5.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.6.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.7.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.8.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.9.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.10.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.11.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.12.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.13.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.14.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.15.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.16.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.17.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.18.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.19.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.20.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.21.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.22.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.23.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.24.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.25.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.26.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.27.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.28.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.29.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.30.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.31.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.32.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.33.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.34.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.35.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.36.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.37.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.38.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.39.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.40.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.41.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.42.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.43.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.44.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.45.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.46.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.47.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.48.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.49.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.50.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.51.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.52.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.53.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.54.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.55.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.56.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.57.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.58.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.59.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.60.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.61.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.62.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.44.mlp.experts.63.up_proj.weight": "model-00113-of-00136.safetensors", - "model.layers.45.mlp.experts.0.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.1.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.2.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.3.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.4.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.5.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.6.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.7.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.8.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.9.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.10.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.11.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.12.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.13.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.14.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.15.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.16.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.17.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.18.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.19.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.20.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.21.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.22.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.23.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.24.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.25.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.26.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.27.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.28.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.29.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.30.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.31.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.32.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.33.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.34.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.35.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.36.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.37.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.38.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.39.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.40.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.41.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.42.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.43.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.44.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.45.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.46.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.47.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.48.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.49.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.50.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.51.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.52.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.53.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.54.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.55.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.56.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.57.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.58.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.59.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.60.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.61.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.62.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.45.mlp.experts.63.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.0.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.1.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.2.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.3.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.4.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.5.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.6.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.7.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.8.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.9.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.10.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.11.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.12.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.13.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.14.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.15.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.16.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.17.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.18.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.19.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.20.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.21.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.22.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.23.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.24.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.25.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.26.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.27.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.28.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.29.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.30.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.31.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.32.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.33.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.34.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.35.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.36.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.37.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.38.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.39.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.40.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.41.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.42.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.43.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.44.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.45.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.46.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.47.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.48.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.49.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.50.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.51.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.52.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.53.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.54.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.55.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.56.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.57.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.58.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.59.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.60.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.61.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.62.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.46.mlp.experts.63.up_proj.weight": "model-00114-of-00136.safetensors", - "model.layers.47.mlp.experts.0.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.1.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.2.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.3.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.4.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.5.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.6.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.7.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.8.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.9.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.10.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.11.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.12.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.13.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.14.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.15.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.16.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.17.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.18.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.19.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.20.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.21.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.22.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.23.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.24.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.25.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.26.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.27.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.28.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.29.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.30.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.31.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.32.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.33.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.34.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.35.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.36.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.37.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.38.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.39.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.40.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.41.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.42.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.43.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.44.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.45.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.46.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.47.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.48.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.49.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.50.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.51.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.52.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.53.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.54.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.55.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.56.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.57.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.58.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.59.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.60.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.61.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.62.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.47.mlp.experts.63.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.0.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.1.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.2.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.3.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.4.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.5.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.6.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.7.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.8.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.9.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.10.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.11.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.12.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.13.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.14.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.15.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.16.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.17.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.18.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.19.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.20.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.21.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.22.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.23.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.24.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.25.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.26.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.27.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.28.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.29.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.30.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.31.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.32.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.33.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.34.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.35.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.36.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.37.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.38.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.39.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.40.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.41.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.42.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.43.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.44.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.45.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.46.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.47.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.48.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.49.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.50.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.51.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.52.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.53.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.54.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.55.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.56.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.57.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.58.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.59.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.60.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.61.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.62.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.48.mlp.experts.63.up_proj.weight": "model-00115-of-00136.safetensors", - "model.layers.49.mlp.experts.0.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.1.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.2.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.3.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.4.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.5.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.6.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.7.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.8.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.9.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.10.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.11.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.12.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.13.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.14.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.15.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.16.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.17.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.18.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.19.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.20.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.21.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.22.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.23.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.24.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.25.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.26.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.27.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.28.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.29.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.30.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.31.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.32.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.33.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.34.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.35.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.36.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.37.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.38.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.39.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.40.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.41.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.42.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.43.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.44.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.45.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.46.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.47.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.48.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.49.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.50.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.51.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.52.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.53.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.54.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.55.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.56.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.57.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.58.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.59.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.60.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.61.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.62.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.49.mlp.experts.63.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.0.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.1.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.2.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.3.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.4.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.5.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.6.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.7.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.8.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.9.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.10.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.11.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.12.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.13.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.14.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.15.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.16.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.17.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.18.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.19.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.20.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.21.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.22.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.23.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.24.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.25.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.26.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.27.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.28.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.29.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.30.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.31.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.32.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.33.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.34.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.35.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.36.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.37.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.38.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.39.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.40.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.41.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.42.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.43.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.44.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.45.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.46.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.47.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.48.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.49.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.50.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.51.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.52.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.53.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.54.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.55.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.56.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.57.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.58.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.59.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.60.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.61.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.62.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.50.mlp.experts.63.up_proj.weight": "model-00116-of-00136.safetensors", - "model.layers.51.mlp.experts.0.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.1.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.2.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.3.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.4.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.5.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.6.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.7.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.8.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.9.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.10.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.11.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.12.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.13.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.14.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.15.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.16.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.17.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.18.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.19.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.20.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.21.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.22.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.23.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.24.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.25.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.26.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.27.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.28.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.29.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.30.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.31.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.32.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.33.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.34.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.35.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.36.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.37.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.38.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.39.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.40.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.41.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.42.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.43.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.44.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.45.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.46.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.47.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.48.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.49.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.50.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.51.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.52.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.53.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.54.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.55.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.56.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.57.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.58.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.59.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.60.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.61.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.62.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.51.mlp.experts.63.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.0.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.1.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.2.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.3.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.4.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.5.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.6.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.7.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.8.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.9.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.10.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.11.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.12.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.13.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.14.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.15.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.16.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.17.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.18.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.19.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.20.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.21.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.22.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.23.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.24.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.25.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.26.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.27.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.28.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.29.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.30.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.31.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.32.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.33.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.34.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.35.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.36.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.37.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.38.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.39.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.40.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.41.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.42.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.43.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.44.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.45.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.46.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.47.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.48.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.49.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.50.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.51.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.52.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.53.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.54.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.55.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.56.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.57.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.58.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.59.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.60.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.61.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.62.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.52.mlp.experts.63.up_proj.weight": "model-00117-of-00136.safetensors", - "model.layers.53.mlp.experts.0.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.1.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.2.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.3.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.4.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.5.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.6.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.7.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.8.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.9.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.10.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.11.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.12.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.13.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.14.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.15.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.16.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.17.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.18.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.19.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.20.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.21.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.22.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.23.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.24.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.25.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.26.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.27.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.28.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.29.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.30.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.31.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.32.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.33.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.34.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.35.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.36.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.37.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.38.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.39.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.40.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.41.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.42.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.43.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.44.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.45.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.46.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.47.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.48.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.49.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.50.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.51.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.52.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.53.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.54.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.55.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.56.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.57.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.58.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.59.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.60.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.61.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.62.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.53.mlp.experts.63.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.0.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.1.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.2.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.3.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.4.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.5.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.6.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.7.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.8.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.9.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.10.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.11.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.12.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.13.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.14.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.15.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.16.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.17.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.18.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.19.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.20.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.21.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.22.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.23.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.24.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.25.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.26.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.27.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.28.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.29.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.30.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.31.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.32.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.33.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.34.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.35.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.36.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.37.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.38.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.39.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.40.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.41.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.42.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.43.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.44.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.45.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.46.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.47.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.48.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.49.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.50.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.51.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.52.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.53.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.54.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.55.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.56.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.57.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.58.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.59.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.60.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.61.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.62.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.54.mlp.experts.63.up_proj.weight": "model-00118-of-00136.safetensors", - "model.layers.55.mlp.experts.0.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.1.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.2.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.3.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.4.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.5.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.6.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.7.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.8.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.9.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.10.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.11.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.12.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.13.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.14.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.15.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.16.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.17.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.18.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.19.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.20.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.21.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.22.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.23.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.24.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.25.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.26.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.27.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.28.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.29.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.30.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.31.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.32.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.33.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.34.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.35.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.36.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.37.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.38.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.39.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.40.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.41.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.42.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.43.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.44.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.45.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.46.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.47.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.48.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.49.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.50.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.51.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.52.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.53.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.54.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.55.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.56.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.57.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.58.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.59.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.60.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.61.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.62.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.55.mlp.experts.63.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.0.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.1.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.2.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.3.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.4.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.5.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.6.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.7.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.8.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.9.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.10.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.11.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.12.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.13.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.14.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.15.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.16.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.17.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.18.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.19.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.20.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.21.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.22.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.23.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.24.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.25.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.26.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.27.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.28.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.29.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.30.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.31.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.32.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.33.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.34.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.35.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.36.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.37.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.38.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.39.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.40.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.41.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.42.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.43.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.44.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.45.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.46.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.47.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.48.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.49.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.50.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.51.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.52.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.53.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.54.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.55.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.56.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.57.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.58.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.59.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.60.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.61.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.62.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.56.mlp.experts.63.up_proj.weight": "model-00119-of-00136.safetensors", - "model.layers.57.mlp.experts.0.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.1.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.2.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.3.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.4.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.5.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.6.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.7.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.8.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.9.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.10.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.11.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.12.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.13.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.14.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.15.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.16.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.17.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.18.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.19.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.20.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.21.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.22.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.23.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.24.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.25.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.26.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.27.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.28.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.29.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.30.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.31.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.32.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.33.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.34.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.35.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.36.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.37.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.38.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.39.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.40.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.41.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.42.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.43.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.44.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.45.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.46.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.47.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.48.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.49.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.50.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.51.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.52.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.53.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.54.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.55.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.56.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.57.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.58.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.59.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.60.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.61.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.62.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.57.mlp.experts.63.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.0.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.1.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.2.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.3.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.4.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.5.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.6.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.7.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.8.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.9.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.10.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.11.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.12.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.13.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.14.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.15.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.16.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.17.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.18.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.19.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.20.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.21.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.22.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.23.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.24.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.25.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.26.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.27.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.28.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.29.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.30.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.31.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.32.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.33.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.34.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.35.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.36.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.37.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.38.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.39.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.40.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.41.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.42.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.43.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.44.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.45.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.46.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.47.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.48.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.49.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.50.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.51.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.52.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.53.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.54.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.55.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.56.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.57.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.58.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.59.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.60.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.61.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.62.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.58.mlp.experts.63.up_proj.weight": "model-00120-of-00136.safetensors", - "model.layers.59.mlp.experts.0.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.1.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.2.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.3.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.4.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.5.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.6.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.7.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.8.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.9.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.10.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.11.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.12.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.13.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.14.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.15.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.16.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.17.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.18.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.19.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.20.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.21.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.22.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.23.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.24.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.25.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.26.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.27.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.28.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.29.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.30.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.31.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.32.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.33.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.34.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.35.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.36.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.37.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.38.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.39.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.40.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.41.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.42.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.43.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.44.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.45.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.46.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.47.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.48.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.49.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.50.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.51.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.52.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.53.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.54.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.55.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.56.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.57.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.58.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.59.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.60.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.61.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.62.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.59.mlp.experts.63.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.0.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.1.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.2.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.3.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.4.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.5.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.6.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.7.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.8.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.9.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.10.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.11.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.12.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.13.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.14.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.15.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.16.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.17.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.18.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.19.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.20.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.21.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.22.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.23.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.24.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.25.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.26.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.27.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.28.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.29.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.30.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.31.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.32.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.33.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.34.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.35.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.36.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.37.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.38.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.39.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.40.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.41.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.42.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.43.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.44.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.45.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.46.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.47.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.48.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.49.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.50.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.51.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.52.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.53.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.54.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.55.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.56.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.57.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.58.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.59.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.60.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.61.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.62.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.60.mlp.experts.63.up_proj.weight": "model-00121-of-00136.safetensors", - "model.layers.61.mlp.experts.0.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.1.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.2.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.3.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.4.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.5.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.6.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.7.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.8.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.9.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.10.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.11.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.12.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.13.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.14.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.15.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.16.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.17.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.18.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.19.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.20.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.21.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.22.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.23.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.24.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.25.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.26.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.27.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.28.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.29.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.30.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.31.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.32.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.33.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.34.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.35.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.36.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.37.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.38.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.39.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.40.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.41.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.42.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.43.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.44.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.45.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.46.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.47.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.48.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.49.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.50.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.51.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.52.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.53.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.54.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.55.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.56.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.57.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.58.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.59.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.60.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.61.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.62.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.61.mlp.experts.63.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.0.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.1.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.2.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.3.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.4.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.5.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.6.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.7.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.8.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.9.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.10.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.11.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.12.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.13.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.14.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.15.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.16.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.17.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.18.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.19.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.20.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.21.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.22.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.23.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.24.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.25.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.26.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.27.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.28.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.29.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.30.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.31.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.32.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.33.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.34.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.35.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.36.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.37.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.38.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.39.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.40.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.41.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.42.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.43.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.44.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.45.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.46.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.47.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.48.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.49.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.50.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.51.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.52.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.53.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.54.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.55.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.56.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.57.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.58.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.59.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.60.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.61.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.62.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.62.mlp.experts.63.up_proj.weight": "model-00122-of-00136.safetensors", - "model.layers.63.mlp.experts.0.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.1.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.2.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.3.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.4.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.5.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.6.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.7.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.8.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.9.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.10.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.11.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.12.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.13.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.14.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.15.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.16.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.17.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.18.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.19.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.20.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.21.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.22.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.23.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.24.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.25.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.26.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.27.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.28.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.29.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.30.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.31.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.32.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.33.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.34.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.35.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.36.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.37.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.38.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.39.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.40.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.41.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.42.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.43.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.44.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.45.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.46.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.47.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.48.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.49.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.50.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.51.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.52.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.53.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.54.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.55.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.56.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.57.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.58.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.59.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.60.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.61.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.62.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.63.mlp.experts.63.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.0.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.1.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.2.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.3.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.4.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.5.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.6.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.7.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.8.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.9.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.10.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.11.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.12.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.13.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.14.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.15.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.16.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.17.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.18.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.19.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.20.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.21.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.22.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.23.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.24.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.25.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.26.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.27.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.28.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.29.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.30.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.31.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.32.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.33.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.34.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.35.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.36.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.37.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.38.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.39.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.40.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.41.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.42.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.43.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.44.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.45.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.46.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.47.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.48.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.49.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.50.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.51.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.52.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.53.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.54.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.55.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.56.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.57.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.58.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.59.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.60.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.61.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.62.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.64.mlp.experts.63.up_proj.weight": "model-00123-of-00136.safetensors", - "model.layers.65.mlp.experts.0.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.1.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.2.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.3.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.4.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.5.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.6.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.7.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.8.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.9.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.10.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.11.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.12.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.13.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.14.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.15.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.16.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.17.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.18.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.19.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.20.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.21.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.22.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.23.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.24.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.25.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.26.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.27.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.28.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.29.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.30.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.31.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.32.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.33.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.34.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.35.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.36.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.37.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.38.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.39.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.40.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.41.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.42.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.43.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.44.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.45.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.46.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.47.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.48.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.49.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.50.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.51.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.52.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.53.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.54.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.55.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.56.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.57.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.58.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.59.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.60.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.61.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.62.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.65.mlp.experts.63.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.0.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.1.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.2.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.3.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.4.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.5.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.6.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.7.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.8.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.9.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.10.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.11.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.12.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.13.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.14.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.15.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.16.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.17.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.18.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.19.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.20.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.21.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.22.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.23.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.24.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.25.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.26.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.27.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.28.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.29.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.30.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.31.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.32.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.33.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.34.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.35.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.36.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.37.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.38.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.39.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.40.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.41.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.42.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.43.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.44.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.45.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.46.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.47.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.48.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.49.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.50.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.51.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.52.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.53.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.54.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.55.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.56.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.57.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.58.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.59.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.60.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.61.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.62.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.66.mlp.experts.63.up_proj.weight": "model-00124-of-00136.safetensors", - "model.layers.67.mlp.experts.0.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.1.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.2.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.3.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.4.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.5.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.6.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.7.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.8.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.9.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.10.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.11.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.12.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.13.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.14.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.15.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.16.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.17.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.18.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.19.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.20.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.21.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.22.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.23.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.24.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.25.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.26.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.27.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.28.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.29.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.30.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.31.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.32.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.33.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.34.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.35.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.36.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.37.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.38.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.39.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.40.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.41.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.42.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.43.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.44.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.45.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.46.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.47.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.48.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.49.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.50.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.51.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.52.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.53.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.54.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.55.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.56.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.57.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.58.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.59.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.60.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.61.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.62.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.67.mlp.experts.63.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.0.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.1.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.2.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.3.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.4.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.5.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.6.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.7.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.8.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.9.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.10.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.11.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.12.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.13.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.14.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.15.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.16.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.17.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.18.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.19.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.20.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.21.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.22.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.23.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.24.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.25.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.26.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.27.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.28.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.29.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.30.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.31.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.32.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.33.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.34.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.35.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.36.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.37.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.38.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.39.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.40.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.41.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.42.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.43.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.44.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.45.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.46.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.47.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.48.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.49.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.50.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.51.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.52.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.53.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.54.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.55.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.56.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.57.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.58.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.59.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.60.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.61.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.62.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.68.mlp.experts.63.up_proj.weight": "model-00125-of-00136.safetensors", - "model.layers.69.mlp.experts.0.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.1.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.2.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.3.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.4.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.5.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.6.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.7.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.8.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.9.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.10.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.11.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.12.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.13.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.14.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.15.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.16.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.17.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.18.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.19.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.20.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.21.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.22.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.23.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.24.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.25.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.26.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.27.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.28.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.29.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.30.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.31.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.32.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.33.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.34.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.35.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.36.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.37.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.38.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.39.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.40.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.41.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.42.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.43.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.44.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.45.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.46.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.47.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.48.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.49.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.50.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.51.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.52.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.53.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.54.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.55.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.56.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.57.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.58.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.59.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.60.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.61.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.62.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.69.mlp.experts.63.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.0.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.1.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.2.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.3.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.4.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.5.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.6.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.7.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.8.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.9.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.10.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.11.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.12.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.13.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.14.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.15.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.16.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.17.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.18.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.19.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.20.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.21.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.22.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.23.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.24.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.25.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.26.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.27.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.28.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.29.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.30.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.31.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.32.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.33.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.34.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.35.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.36.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.37.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.38.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.39.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.40.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.41.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.42.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.43.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.44.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.45.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.46.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.47.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.48.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.49.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.50.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.51.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.52.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.53.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.54.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.55.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.56.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.57.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.58.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.59.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.60.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.61.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.62.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.70.mlp.experts.63.up_proj.weight": "model-00126-of-00136.safetensors", - "model.layers.71.mlp.experts.0.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.1.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.2.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.3.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.4.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.5.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.6.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.7.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.8.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.9.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.10.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.11.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.12.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.13.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.14.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.15.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.16.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.17.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.18.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.19.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.20.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.21.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.22.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.23.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.24.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.25.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.26.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.27.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.28.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.29.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.30.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.31.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.32.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.33.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.34.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.35.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.36.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.37.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.38.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.39.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.40.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.41.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.42.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.43.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.44.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.45.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.46.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.47.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.48.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.49.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.50.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.51.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.52.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.53.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.54.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.55.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.56.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.57.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.58.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.59.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.60.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.61.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.62.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.71.mlp.experts.63.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.0.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.1.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.2.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.3.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.4.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.5.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.6.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.7.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.8.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.9.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.10.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.11.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.12.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.13.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.14.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.15.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.16.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.17.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.18.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.19.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.20.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.21.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.22.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.23.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.24.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.25.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.26.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.27.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.28.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.29.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.30.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.31.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.32.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.33.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.34.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.35.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.36.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.37.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.38.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.39.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.40.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.41.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.42.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.43.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.44.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.45.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.46.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.47.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.48.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.49.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.50.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.51.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.52.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.53.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.54.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.55.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.56.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.57.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.58.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.59.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.60.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.61.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.62.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.72.mlp.experts.63.up_proj.weight": "model-00127-of-00136.safetensors", - "model.layers.73.mlp.experts.0.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.1.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.2.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.3.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.4.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.5.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.6.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.7.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.8.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.9.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.10.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.11.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.12.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.13.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.14.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.15.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.16.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.17.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.18.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.19.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.20.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.21.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.22.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.23.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.24.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.25.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.26.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.27.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.28.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.29.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.30.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.31.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.32.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.33.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.34.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.35.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.36.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.37.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.38.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.39.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.40.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.41.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.42.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.43.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.44.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.45.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.46.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.47.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.48.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.49.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.50.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.51.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.52.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.53.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.54.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.55.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.56.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.57.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.58.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.59.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.60.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.61.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.62.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.73.mlp.experts.63.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.0.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.1.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.2.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.3.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.4.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.5.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.6.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.7.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.8.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.9.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.10.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.11.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.12.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.13.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.14.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.15.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.16.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.17.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.18.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.19.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.20.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.21.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.22.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.23.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.24.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.25.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.26.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.27.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.28.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.29.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.30.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.31.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.32.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.33.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.34.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.35.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.36.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.37.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.38.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.39.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.40.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.41.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.42.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.43.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.44.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.45.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.46.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.47.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.48.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.49.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.50.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.51.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.52.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.53.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.54.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.55.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.56.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.57.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.58.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.59.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.60.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.61.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.62.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.74.mlp.experts.63.up_proj.weight": "model-00128-of-00136.safetensors", - "model.layers.75.mlp.experts.0.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.1.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.2.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.3.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.4.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.5.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.6.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.7.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.8.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.9.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.10.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.11.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.12.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.13.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.14.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.15.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.16.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.17.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.18.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.19.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.20.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.21.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.22.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.23.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.24.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.25.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.26.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.27.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.28.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.29.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.30.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.31.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.32.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.33.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.34.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.35.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.36.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.37.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.38.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.39.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.40.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.41.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.42.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.43.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.44.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.45.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.46.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.47.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.48.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.49.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.50.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.51.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.52.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.53.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.54.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.55.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.56.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.57.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.58.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.59.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.60.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.61.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.62.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.75.mlp.experts.63.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.0.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.1.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.2.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.3.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.4.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.5.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.6.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.7.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.8.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.9.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.10.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.11.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.12.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.13.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.14.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.15.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.16.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.17.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.18.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.19.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.20.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.21.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.22.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.23.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.24.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.25.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.26.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.27.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.28.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.29.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.30.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.31.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.32.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.33.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.34.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.35.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.36.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.37.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.38.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.39.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.40.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.41.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.42.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.43.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.44.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.45.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.46.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.47.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.48.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.49.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.50.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.51.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.52.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.53.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.54.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.55.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.56.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.57.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.58.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.59.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.60.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.61.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.62.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.76.mlp.experts.63.up_proj.weight": "model-00129-of-00136.safetensors", - "model.layers.77.mlp.experts.0.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.1.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.2.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.3.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.4.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.5.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.6.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.7.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.8.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.9.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.10.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.11.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.12.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.13.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.14.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.15.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.16.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.17.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.18.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.19.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.20.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.21.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.22.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.23.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.24.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.25.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.26.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.27.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.28.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.29.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.30.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.31.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.32.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.33.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.34.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.35.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.36.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.37.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.38.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.39.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.40.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.41.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.42.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.43.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.44.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.45.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.46.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.47.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.48.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.49.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.50.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.51.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.52.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.53.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.54.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.55.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.56.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.57.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.58.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.59.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.60.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.61.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.62.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.77.mlp.experts.63.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.0.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.1.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.2.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.3.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.4.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.5.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.6.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.7.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.8.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.9.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.10.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.11.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.12.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.13.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.14.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.15.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.16.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.17.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.18.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.19.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.20.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.21.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.22.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.23.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.24.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.25.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.26.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.27.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.28.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.29.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.30.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.31.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.32.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.33.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.34.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.35.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.36.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.37.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.38.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.39.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.40.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.41.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.42.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.43.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.44.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.45.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.46.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.47.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.48.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.49.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.50.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.51.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.52.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.53.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.54.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.55.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.56.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.57.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.58.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.59.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.60.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.61.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.62.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.78.mlp.experts.63.up_proj.weight": "model-00130-of-00136.safetensors", - "model.layers.79.mlp.experts.0.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.1.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.2.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.3.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.4.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.5.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.6.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.7.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.8.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.9.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.10.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.11.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.12.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.13.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.14.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.15.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.16.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.17.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.18.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.19.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.20.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.21.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.22.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.23.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.24.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.25.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.26.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.27.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.28.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.29.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.30.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.31.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.32.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.33.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.34.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.35.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.36.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.37.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.38.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.39.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.40.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.41.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.42.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.43.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.44.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.45.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.46.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.47.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.48.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.49.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.50.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.51.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.52.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.53.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.54.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.55.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.56.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.57.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.58.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.59.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.60.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.61.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.62.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.79.mlp.experts.63.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.0.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.1.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.2.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.3.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.4.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.5.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.6.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.7.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.8.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.9.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.10.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.11.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.12.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.13.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.14.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.15.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.16.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.17.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.18.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.19.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.20.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.21.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.22.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.23.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.24.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.25.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.26.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.27.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.28.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.29.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.30.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.31.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.32.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.33.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.34.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.35.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.36.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.37.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.38.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.39.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.40.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.41.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.42.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.43.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.44.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.45.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.46.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.47.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.48.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.49.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.50.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.51.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.52.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.53.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.54.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.55.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.56.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.57.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.58.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.59.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.60.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.61.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.62.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.80.mlp.experts.63.up_proj.weight": "model-00131-of-00136.safetensors", - "model.layers.81.mlp.experts.0.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.1.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.2.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.3.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.4.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.5.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.6.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.7.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.8.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.9.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.10.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.11.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.12.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.13.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.14.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.15.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.16.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.17.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.18.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.19.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.20.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.21.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.22.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.23.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.24.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.25.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.26.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.27.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.28.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.29.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.30.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.31.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.32.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.33.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.34.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.35.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.36.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.37.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.38.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.39.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.40.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.41.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.42.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.43.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.44.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.45.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.46.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.47.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.48.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.49.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.50.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.51.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.52.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.53.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.54.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.55.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.56.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.57.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.58.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.59.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.60.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.61.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.62.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.81.mlp.experts.63.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.0.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.1.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.2.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.3.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.4.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.5.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.6.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.7.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.8.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.9.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.10.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.11.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.12.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.13.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.14.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.15.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.16.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.17.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.18.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.19.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.20.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.21.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.22.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.23.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.24.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.25.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.26.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.27.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.28.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.29.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.30.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.31.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.32.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.33.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.34.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.35.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.36.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.37.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.38.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.39.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.40.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.41.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.42.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.43.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.44.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.45.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.46.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.47.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.48.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.49.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.50.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.51.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.52.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.53.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.54.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.55.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.56.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.57.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.58.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.59.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.60.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.61.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.62.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.82.mlp.experts.63.up_proj.weight": "model-00132-of-00136.safetensors", - "model.layers.83.mlp.experts.0.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.1.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.2.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.3.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.4.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.5.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.6.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.7.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.8.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.9.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.10.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.11.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.12.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.13.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.14.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.15.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.16.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.17.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.18.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.19.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.20.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.21.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.22.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.23.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.24.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.25.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.26.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.27.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.28.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.29.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.30.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.31.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.32.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.33.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.34.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.35.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.36.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.37.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.38.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.39.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.40.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.41.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.42.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.43.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.44.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.45.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.46.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.47.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.48.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.49.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.50.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.51.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.52.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.53.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.54.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.55.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.56.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.57.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.58.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.59.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.60.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.61.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.62.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.83.mlp.experts.63.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.0.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.1.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.2.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.3.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.4.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.5.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.6.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.7.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.8.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.9.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.10.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.11.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.12.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.13.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.14.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.15.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.16.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.17.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.18.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.19.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.20.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.21.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.22.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.23.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.24.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.25.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.26.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.27.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.28.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.29.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.30.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.31.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.32.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.33.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.34.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.35.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.36.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.37.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.38.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.39.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.40.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.41.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.42.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.43.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.44.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.45.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.46.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.47.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.48.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.49.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.50.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.51.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.52.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.53.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.54.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.55.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.56.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.57.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.58.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.59.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.60.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.61.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.62.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.84.mlp.experts.63.up_proj.weight": "model-00133-of-00136.safetensors", - "model.layers.85.mlp.experts.0.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.1.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.2.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.3.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.4.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.5.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.6.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.7.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.8.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.9.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.10.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.11.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.12.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.13.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.14.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.15.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.16.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.17.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.18.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.19.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.20.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.21.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.22.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.23.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.24.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.25.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.26.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.27.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.28.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.29.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.30.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.31.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.32.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.33.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.34.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.35.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.36.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.37.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.38.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.39.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.40.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.41.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.42.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.43.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.44.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.45.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.46.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.47.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.48.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.49.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.50.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.51.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.52.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.53.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.54.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.55.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.56.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.57.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.58.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.59.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.60.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.61.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.62.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.85.mlp.experts.63.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.0.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.1.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.2.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.3.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.4.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.5.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.6.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.7.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.8.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.9.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.10.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.11.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.12.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.13.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.14.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.15.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.16.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.17.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.18.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.19.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.20.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.21.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.22.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.23.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.24.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.25.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.26.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.27.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.28.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.29.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.30.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.31.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.32.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.33.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.34.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.35.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.36.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.37.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.38.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.39.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.40.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.41.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.42.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.43.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.44.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.45.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.46.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.47.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.48.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.49.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.50.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.51.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.52.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.53.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.54.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.55.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.56.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.57.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.58.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.59.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.60.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.61.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.62.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.86.mlp.experts.63.up_proj.weight": "model-00134-of-00136.safetensors", - "model.layers.87.mlp.experts.0.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.1.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.2.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.3.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.4.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.5.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.6.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.7.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.8.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.9.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.10.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.11.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.12.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.13.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.14.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.15.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.16.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.17.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.18.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.19.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.20.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.21.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.22.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.23.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.24.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.25.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.26.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.27.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.28.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.29.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.30.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.31.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.32.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.33.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.34.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.35.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.36.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.37.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.38.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.39.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.40.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.41.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.42.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.43.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.44.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.45.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.46.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.47.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.48.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.49.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.50.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.51.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.52.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.53.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.54.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.55.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.56.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.57.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.58.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.59.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.60.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.61.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.62.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.experts.63.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.0.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.62.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.63.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.64.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.65.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.66.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.67.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.68.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.69.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.70.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.71.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.72.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.73.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.74.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.75.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.76.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.77.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.78.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.79.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.80.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.81.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.82.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.83.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.84.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.85.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.86.mlp.shared_experts.up_proj.weight": "model-00135-of-00136.safetensors", - "model.layers.87.mlp.shared_experts.up_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.0.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.62.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.63.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.64.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.65.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.66.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.67.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.68.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.69.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.70.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.71.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.72.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.73.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.74.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.75.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.76.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.77.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.78.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.79.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.80.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.81.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.82.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.83.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.84.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.85.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.86.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors", - "model.layers.87.mlp.shared_experts.down_proj.weight": "model-00136-of-00136.safetensors" - } -} \ No newline at end of file