diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..9e1b0d12bc5d737cb3ad34fadd8b2321851a6c2a --- /dev/null +++ b/README.md @@ -0,0 +1,53 @@ +--- +base_model: +- win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +library_name: transformers +tags: +- mergekit +- merge + +--- +# merge + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the passthrough merge method. + +### Models Merged + +The following models were included in the merge: +* [win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B](https://huggingface.co/win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +dtype: bfloat16 +merge_method: passthrough +slices: +- sources: + - layer_range: [0, 8] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [4, 12] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [8, 16] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [12, 20] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [16, 24] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [20, 28] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [24, 32] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..25f09abc2dbd26783bd0da15660be836c2c36f6b --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "_name_or_path": "win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 56, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.2", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..df397a3db0a3780e108acfb40c871afb05a22c10 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,24 @@ +dtype: bfloat16 +merge_method: passthrough +slices: +- sources: + - layer_range: [0, 8] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [4, 12] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [8, 16] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [12, 20] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [16, 24] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [20, 28] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B +- sources: + - layer_range: [24, 32] + model: win10/Infinirc-ArliAI-RPMax-v1.3-merge-8B \ No newline at end of file diff --git a/model-00001-of-00058.safetensors b/model-00001-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b557876ba2c72b4f59a9bf87186a21bd1366695 --- /dev/null +++ b/model-00001-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5321ca97dd0968a3e2b676b3a42728e9f5327d516bcf0addd4e9cd61c068a1ad +size 1050673280 diff --git a/model-00002-of-00058.safetensors b/model-00002-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f2f39fec0c389625b9d309edcfb70671a6e2bd8 --- /dev/null +++ b/model-00002-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3bea19802752659d8f54d4b3a0b4ec96c6d65c89ce4d72c9cf14952e3d0ef1f +size 1050673296 diff --git a/model-00003-of-00058.safetensors b/model-00003-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..381960cb0dfa684a0ac84b8858d87dc94251d152 --- /dev/null +++ b/model-00003-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed63a90398db79bc8cdb931e9fb097aec913cc786d7f08f3cefd1540e489943 +size 436233352 diff --git a/model-00004-of-00058.safetensors b/model-00004-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..992dfd2ad8c886961a06d4c7b64bf55a9046f606 --- /dev/null +++ b/model-00004-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f75f97ea5dbcf082b7a07196361eaa44bb34c5613487ca5ada5a907cb73767 +size 436233360 diff --git a/model-00005-of-00058.safetensors b/model-00005-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1148c23845ca71182112a7b2f932bd949fe60dce --- /dev/null +++ b/model-00005-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259076f589d6633968058004e2907846a32ef8440d680aceebc0e0927690916c +size 469762536 diff --git a/model-00006-of-00058.safetensors b/model-00006-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15477b1f8d2fff7ae0bc4aae46537ee183ae1821 --- /dev/null +++ b/model-00006-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d32269a40630c6cdeeadacb6bff1af610ebdf45a2b5f3e0c790cfaa9dbd5c4 +size 402687600 diff --git a/model-00007-of-00058.safetensors b/model-00007-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2d4f6e9a38e6551e1e575df96103fa846120d97 --- /dev/null +++ b/model-00007-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd85e9157842b6d89397c8593b5b3a55de60f88a531170133dc05b8b456cf010 +size 469762536 diff --git a/model-00008-of-00058.safetensors b/model-00008-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..03f13619c9580d83b851a9054d65b47bcc986dac --- /dev/null +++ b/model-00008-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e67b20fcc1f45d43889f3af29a8631cb592b9d3fcd3c12ac21caa798b401c8b +size 402687600 diff --git a/model-00009-of-00058.safetensors b/model-00009-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..27b5230bdc0056e7db54ea04ba9760fda93a97c4 --- /dev/null +++ b/model-00009-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7caee7320881eb8139d2bb1318cbc3fe4c8abb25758802b85058667f47cab950 +size 469762536 diff --git a/model-00010-of-00058.safetensors b/model-00010-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a180041bcab37dda841f4255462d984295cbf2b3 --- /dev/null +++ b/model-00010-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a267d1de7c854eecfe3edf60af41fc273e488f190d09693b5f064227d6d53aa +size 402687600 diff --git a/model-00011-of-00058.safetensors b/model-00011-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..306f53237a2a4c387c5cc4b7e22027224ccc37ef --- /dev/null +++ b/model-00011-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6bb7568a61abcde7e1dc9ff4bd34c960cc04a576d416bad5a52c12634b2137a +size 469762536 diff --git a/model-00012-of-00058.safetensors b/model-00012-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..734d697f17ba3bf35ec0fbe324ca1e0847b8a05e --- /dev/null +++ b/model-00012-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f184ddd2c65fd2bd056645639fde601127af49ffbf25936776208670ab78ab +size 402687600 diff --git a/model-00013-of-00058.safetensors b/model-00013-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..505862ea490c3bbf318f2ec4dda5a9298529db0e --- /dev/null +++ b/model-00013-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f36a584c5ce68050424d90167a5da56fc9d5c4bfd511f515cf9f2a80e27e39 +size 469762536 diff --git a/model-00014-of-00058.safetensors b/model-00014-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..267d4aee965bf2e9dad7bd954d3eac8d8b44674a --- /dev/null +++ b/model-00014-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a9336d64088d83e72d52dad82ee1976a057eee6e9c021cd53152e537ab2fce +size 402687600 diff --git a/model-00015-of-00058.safetensors b/model-00015-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12ba5d9075c6236b42f303a36540e4cf9185336c --- /dev/null +++ b/model-00015-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61837d8837af4eabe7b879cec1a09f2e9ed04852e0f2f278a01798fffa9c6efc +size 469762536 diff --git a/model-00016-of-00058.safetensors b/model-00016-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94e02332cbc510cd021b08bea425c7ca20c55edc --- /dev/null +++ b/model-00016-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd7a720539434f4cc019d6bb5196131d5632fb9538f8b0f0653421b3e6addbfd +size 402687600 diff --git a/model-00017-of-00058.safetensors b/model-00017-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a9b8163f43205d9776a6788bb24b7e54ddb38fa --- /dev/null +++ b/model-00017-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f38c106643e789143c70acd0f9916956d76124ac5b6150ee3d3c1a0bdb117bc8 +size 469762536 diff --git a/model-00018-of-00058.safetensors b/model-00018-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fb2112a5a0f4fec541f538ab90a5ba32b5018d4 --- /dev/null +++ b/model-00018-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a57b3a8fc7a01dc767c9fad9e8c5cb6777b7dfc091b3aaf0bce00b874b89027 +size 402687600 diff --git a/model-00019-of-00058.safetensors b/model-00019-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5119232867f0c4b0e5fa1c00dd56b6194e53203a --- /dev/null +++ b/model-00019-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f11a3fab893c7f239787f4b792f921a2cd2c493feeae497d6c662313f56c1e6f +size 469762536 diff --git a/model-00020-of-00058.safetensors b/model-00020-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..992822be6cc32472ec22bb7715ab2a2d2b0568af --- /dev/null +++ b/model-00020-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:312458c14e2add61ce86d740d40ca518b89f03bba026deead5d9b4120460a994 +size 402687600 diff --git a/model-00021-of-00058.safetensors b/model-00021-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e99a811c45e76ae6abab844f5b5df0922222955 --- /dev/null +++ b/model-00021-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3556956377293b1d40943358e04e70b56ee6d83467c2b8115ab6b1ec382886 +size 469762536 diff --git a/model-00022-of-00058.safetensors b/model-00022-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee437b3c699fc3806b566d157a561b8601a6e809 --- /dev/null +++ b/model-00022-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643f4e3209ade93a1fadab58fefc436ca4135bf60fd02b5ddcd6a655fc771190 +size 402687600 diff --git a/model-00023-of-00058.safetensors b/model-00023-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..89f02e00b0c1e259079f8ec43c78163198247a7f --- /dev/null +++ b/model-00023-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0a335bda9c20817c4d61e2b0bd51143d729d0ac8356dcf69deb95bc34f8fdb +size 469762536 diff --git a/model-00024-of-00058.safetensors b/model-00024-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..81212d8f37081b24814876a8c8966ab145dc5662 --- /dev/null +++ b/model-00024-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a484e8ed1d079acd9d06a2d88fbd780c6331d546add7e91a2039cee830915715 +size 402679288 diff --git a/model-00025-of-00058.safetensors b/model-00025-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01a86a296b51e16049e8d4f32a166039cb462238 --- /dev/null +++ b/model-00025-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd8a05c8765c71f4b228ec28f2d60e6ad8bbbe9ff32558f9b573e5b61dc96f58 +size 436233360 diff --git a/model-00026-of-00058.safetensors b/model-00026-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8deee02c64dd110a6e92d089eda709341a44f45b --- /dev/null +++ b/model-00026-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb759c11b9bfa967eee7e4a34aa74dcb3eba7950d194bc1739b6552a2efd516 +size 469762536 diff --git a/model-00027-of-00058.safetensors b/model-00027-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a61b67ff1081e598572ba22f671ec6f8d5d11b62 --- /dev/null +++ b/model-00027-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07cfd07ab9a65f9b1ffa71dff5073e9ad8fd805a8add76d4047aa14cc82d9cac +size 402687600 diff --git a/model-00028-of-00058.safetensors b/model-00028-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0ed47504fbefef69b8bc6b6bece45ad6273e717 --- /dev/null +++ b/model-00028-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1576386c3872364a3052f20a6e0412b6ab4ccfcbdd16d45c83c1f87ca90b83fe +size 469762536 diff --git a/model-00029-of-00058.safetensors b/model-00029-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..144c93b27d3b314ea1cb422d1eebb1a6e7311f0f --- /dev/null +++ b/model-00029-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c045bd5a147f7f4fb048eed102e55ce6df64efba965a7786c8f47b43d9f06d +size 402687600 diff --git a/model-00030-of-00058.safetensors b/model-00030-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1eb0430f7220c4fa178bbc0eeb7470372bfda790 --- /dev/null +++ b/model-00030-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1862f2c02e1e586af058909586d8fda3fcc93211b39a074ddaf77f4c773a2ce2 +size 469762536 diff --git a/model-00031-of-00058.safetensors b/model-00031-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c15617417ea608bce707259a88d1a7f80aeb4dfe --- /dev/null +++ b/model-00031-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5b7311c3f5d92911676f86b6314cf9a12b852848374af5a780ade99718dba9 +size 402687600 diff --git a/model-00032-of-00058.safetensors b/model-00032-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fef4d246ea9ec7932d9e18c326b0342a07a68637 --- /dev/null +++ b/model-00032-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdbbd14538d90e0815f47a77739ea6842a5aa3e67034f03e8ba449d13dcd6ac9 +size 469762536 diff --git a/model-00033-of-00058.safetensors b/model-00033-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5612fa177c0c8e16369c07466d129ac4a68e105 --- /dev/null +++ b/model-00033-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7d72872dca6ec28ffdc27e6689d323fb36dbf09d9c9d655e185821afac2885c +size 402687600 diff --git a/model-00034-of-00058.safetensors b/model-00034-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c53b1f50e9cc5aaceb9bc8f5fe573959e969ea00 --- /dev/null +++ b/model-00034-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c7288b0ddc1a5401516ad7ada194d144e34242d9077f94aa2102cb145cae517 +size 469762536 diff --git a/model-00035-of-00058.safetensors b/model-00035-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c149c7e466a0ff11df9d9808c9688ede7d982bd4 --- /dev/null +++ b/model-00035-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ce90615d9c8996f4f6d9ef69b27faff591dda30305a7d0d456e0d50f1b904c +size 402687600 diff --git a/model-00036-of-00058.safetensors b/model-00036-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4331270f53d6784745b5301cddbdef4442ab0236 --- /dev/null +++ b/model-00036-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0b69007a17cc92555ea86135e81be339c9475e4a100df02d761e3c0a9a46e1 +size 469762536 diff --git a/model-00037-of-00058.safetensors b/model-00037-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51eadb5d1b8f64aa5e646d45ca0eb94ac723a7c3 --- /dev/null +++ b/model-00037-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a7e35a852b69ede80fe5d15977a914be9bbdd456f3100247c65b83a4d5bedc1 +size 402687600 diff --git a/model-00038-of-00058.safetensors b/model-00038-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc715ce335a3ab86df60f8ef8c5917e10edb3866 --- /dev/null +++ b/model-00038-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8acde7cdd4905e6de765259c56fe14f57d044f473145275938bd4958495060c0 +size 469762536 diff --git a/model-00039-of-00058.safetensors b/model-00039-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f41e9a05e52740123313717cea0c41f3ba0b097 --- /dev/null +++ b/model-00039-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a0ba8eed8a221427dec3553c6a11e07855557e8fa35a5f41e14ee0240f8530 +size 402687600 diff --git a/model-00040-of-00058.safetensors b/model-00040-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66330d92214f94578666f8bd7ecd618e9a007688 --- /dev/null +++ b/model-00040-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea5fe1ebc083b8184ff4535a2e180e2bd4910c3b74bf6cdec9463387aaad0bc +size 469762536 diff --git a/model-00041-of-00058.safetensors b/model-00041-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d3be8a875bdbe18164c6f53d879edc0ec051777 --- /dev/null +++ b/model-00041-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89dcdbc0d3376821a49475f40bd1da99e156bb93a222b55f32183816f2cf40ad +size 402679296 diff --git a/model-00042-of-00058.safetensors b/model-00042-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a391ee01dbb17801fd2b9738c5a48a6736d1c980 --- /dev/null +++ b/model-00042-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c74f551b75d477eb61f39e3d9054b3cdbfcfd93a7562a8bfbc9b0f2c3111de2 +size 436225072 diff --git a/model-00043-of-00058.safetensors b/model-00043-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..178f98345cca55fe93eb804cac1e844302ef1ae9 --- /dev/null +++ b/model-00043-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7f8561db29a83b7bff9993f546ae1b0e46a65547bba4b0b43fbd7f2d54aabec +size 436225056 diff --git a/model-00044-of-00058.safetensors b/model-00044-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..caa7835b8886ea26262d5208a4573feabcf51d23 --- /dev/null +++ b/model-00044-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99a5343ed6a52a6bb81f2ff1c9a00436da1510358923ea383044bc79c3fda6e9 +size 436225064 diff --git a/model-00045-of-00058.safetensors b/model-00045-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33dc8f43346817df9a71870abc7c50f185248605 --- /dev/null +++ b/model-00045-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e0d3eed11e37683adfd33118a02a2630c4a5f6d693c77aa24ff77a2a373b41 +size 436225072 diff --git a/model-00046-of-00058.safetensors b/model-00046-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ca796e12640ecc4c93ec0cd2e34813d8568f2c5 --- /dev/null +++ b/model-00046-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23f59d5da8826ca074ad761c82553ed62a38d3885abbd2e58ab224612540aa4 +size 436233360 diff --git a/model-00047-of-00058.safetensors b/model-00047-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8159bfab6f841cc197240268962a0e3de45ed005 --- /dev/null +++ b/model-00047-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2225e0e9655ffd0b510e7417267a43afd07362a30e11dcbd657c616b87f1d688 +size 469762536 diff --git a/model-00048-of-00058.safetensors b/model-00048-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..452e353fc2186a4542b9ab63b18cf0e4e8e79c32 --- /dev/null +++ b/model-00048-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e267892dbc45fac5e57b8f84f353dd92707a4ea3b03b9ca6b3bbce44dfcddbb +size 402687584 diff --git a/model-00049-of-00058.safetensors b/model-00049-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1783cf2dd8cf5f485468dda3906f1ae929e5c1a2 --- /dev/null +++ b/model-00049-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c44a36723ddf9591933ad6e2d62514b71aa4400729e6073db88b2161ed827d03 +size 469762536 diff --git a/model-00050-of-00058.safetensors b/model-00050-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb38e75bf115331f814d53261876886e4963655e --- /dev/null +++ b/model-00050-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc89f39880967f22a41c8f292efc463c05426b9e74c1e87ca2662631ae19667 +size 402687576 diff --git a/model-00051-of-00058.safetensors b/model-00051-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e7b37adc7ec2afbada3c6a668b128d247bbdc82 --- /dev/null +++ b/model-00051-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ea5b48b239c9100ee32e6dae9e723b39c6a034b33b3608e72ed4a1666e8d7a +size 469762536 diff --git a/model-00052-of-00058.safetensors b/model-00052-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ddb856acff00faf5f2a8cdd533db0f55474fa097 --- /dev/null +++ b/model-00052-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49269374d40e1bd8bfcec2edab02ba8fab08ba43b2126803b184cb50f9ddf879 +size 402687592 diff --git a/model-00053-of-00058.safetensors b/model-00053-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4890fa9d9b717d56e17ee41c8d18afbffa5d66d3 --- /dev/null +++ b/model-00053-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137e124e11716db7b61e7a585cdaa6115d86a6b8c1dae2fe18b113e9d9cfa188 +size 469762536 diff --git a/model-00054-of-00058.safetensors b/model-00054-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..175d6fd34a412bd0a5a79043828f57b2d8ad4ffe --- /dev/null +++ b/model-00054-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed03fb8a0246952e747a3adc79003d9a7d74de21e38bd6650e401a4c04736f19 +size 402687592 diff --git a/model-00055-of-00058.safetensors b/model-00055-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8dced72b52f5134ab83e9559a40022347b10fccd --- /dev/null +++ b/model-00055-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eaf203c2b4e91c9aa3606044a7c86af1f223caf233ec036bcb3ad5b0233a970 +size 469762536 diff --git a/model-00056-of-00058.safetensors b/model-00056-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15cabe055d9bda36ac2ab6f69e2b67f8af56fc83 --- /dev/null +++ b/model-00056-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4f664794cf560e1510b41f66431f60fc187432acce25d156a6f53d491f7a38 +size 402687600 diff --git a/model-00057-of-00058.safetensors b/model-00057-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3d23fb231ea0fa38d996c60675c85e7f1e93b46 --- /dev/null +++ b/model-00057-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ac9d863cba8ad8fa4a3a91e7d6f474a1b9f3dbe43732a2908964288a0d4449a +size 469762536 diff --git a/model-00058-of-00058.safetensors b/model-00058-of-00058.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..238bae2c68bf49c36109d004207ad3e6359104e8 --- /dev/null +++ b/model-00058-of-00058.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6080d4a933f0c01c2554644d79181b4b3de0d7182bef199bab0a7b531743ad05 +size 402679272 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..e45a3f3dda787552392b6b203e97bee17b46bf19 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 26529898496}, "weight_map": {"lm_head.weight": "model-00001-of-00058.safetensors", "model.embed_tokens.weight": "model-00002-of-00058.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00058.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00058.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00058.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00058.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00058.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00058.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00058.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00058.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00058.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00058.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00058.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00058.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00058.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00058.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00058.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00058.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00058.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00058.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00058.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00058.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00058.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00058.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00058.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00058.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00058.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00058.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00058.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00058.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00058.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00058.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00058.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00058.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00058.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00058.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00058.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00058.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00058.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00058.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00058.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00058.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00058.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00058.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00058.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00058.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00058.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00058.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00058.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00058.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00058.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00058.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00058.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00058.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00058.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00058.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00058.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00058.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00058.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00058.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00058.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00058.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00058.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00058.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00058.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00058.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00058.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00058.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00058.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00058.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00058.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00058.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00058.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00058.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00058.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00058.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00058.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00058.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00058.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00058.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00058.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00012-of-00058.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00058.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00058.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00058.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00058.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00058.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00058.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00058.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00058.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00058.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00058.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00058.safetensors", "model.layers.22.input_layernorm.weight": "model-00012-of-00058.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00013-of-00058.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00058.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00058.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00058.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00058.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00058.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00058.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00058.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00058.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00058.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00058.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00058.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00058.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00058.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00058.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00058.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00058.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00058.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00015-of-00058.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00058.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00058.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00058.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00016-of-00058.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00016-of-00058.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00016-of-00058.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00058.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00058.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00058.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00058.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00058.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00058.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00058.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00058.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00058.safetensors", "model.layers.32.input_layernorm.weight": "model-00016-of-00058.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00058.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00017-of-00058.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00017-of-00058.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00017-of-00058.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00058.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00018-of-00058.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00018-of-00058.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00058.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00058.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00058.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00018-of-00058.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00058.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00018-of-00058.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00058.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00058.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00058.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00018-of-00058.safetensors", "model.layers.33.input_layernorm.weight": "model-00018-of-00058.safetensors", "model.layers.29.input_layernorm.weight": "model-00018-of-00058.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00019-of-00058.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00019-of-00058.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00019-of-00058.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00019-of-00058.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00020-of-00058.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00058.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00058.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00058.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00058.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00058.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00058.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00058.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00058.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00058.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00058.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00058.safetensors", "model.layers.34.input_layernorm.weight": "model-00020-of-00058.safetensors", "model.layers.30.input_layernorm.weight": "model-00020-of-00058.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00021-of-00058.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00021-of-00058.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00021-of-00058.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00058.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00022-of-00058.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00022-of-00058.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00022-of-00058.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00058.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00022-of-00058.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00058.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00022-of-00058.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00058.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00022-of-00058.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00058.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00022-of-00058.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00058.safetensors", "model.layers.35.input_layernorm.weight": "model-00022-of-00058.safetensors", "model.layers.31.input_layernorm.weight": "model-00022-of-00058.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00023-of-00058.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00023-of-00058.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00023-of-00058.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00023-of-00058.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00024-of-00058.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00024-of-00058.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00024-of-00058.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00024-of-00058.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00024-of-00058.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00024-of-00058.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00024-of-00058.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00024-of-00058.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00024-of-00058.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00058.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00024-of-00058.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00024-of-00058.safetensors", "model.layers.2.input_layernorm.weight": "model-00024-of-00058.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00025-of-00058.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00025-of-00058.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00025-of-00058.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00025-of-00058.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00025-of-00058.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00025-of-00058.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00025-of-00058.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00025-of-00058.safetensors", "model.layers.40.input_layernorm.weight": "model-00025-of-00058.safetensors", "model.layers.36.input_layernorm.weight": "model-00025-of-00058.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00026-of-00058.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00026-of-00058.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00026-of-00058.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00026-of-00058.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00027-of-00058.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00027-of-00058.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00027-of-00058.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00027-of-00058.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00027-of-00058.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00027-of-00058.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00027-of-00058.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00027-of-00058.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00027-of-00058.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00027-of-00058.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00027-of-00058.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00027-of-00058.safetensors", "model.layers.41.input_layernorm.weight": "model-00027-of-00058.safetensors", "model.layers.37.input_layernorm.weight": "model-00027-of-00058.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00028-of-00058.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00028-of-00058.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00028-of-00058.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00028-of-00058.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00029-of-00058.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00029-of-00058.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00029-of-00058.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00029-of-00058.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00029-of-00058.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00029-of-00058.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00029-of-00058.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00029-of-00058.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00029-of-00058.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00029-of-00058.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00029-of-00058.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00029-of-00058.safetensors", "model.layers.42.input_layernorm.weight": "model-00029-of-00058.safetensors", "model.layers.38.input_layernorm.weight": "model-00029-of-00058.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00030-of-00058.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00030-of-00058.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00030-of-00058.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00030-of-00058.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00031-of-00058.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00031-of-00058.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00031-of-00058.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00031-of-00058.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00031-of-00058.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00031-of-00058.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00031-of-00058.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00031-of-00058.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00031-of-00058.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00031-of-00058.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00031-of-00058.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00031-of-00058.safetensors", "model.layers.43.input_layernorm.weight": "model-00031-of-00058.safetensors", "model.layers.39.input_layernorm.weight": "model-00031-of-00058.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00032-of-00058.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00032-of-00058.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00032-of-00058.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00032-of-00058.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00033-of-00058.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00033-of-00058.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00033-of-00058.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00033-of-00058.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00033-of-00058.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00033-of-00058.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00033-of-00058.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00033-of-00058.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00033-of-00058.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00033-of-00058.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00033-of-00058.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00033-of-00058.safetensors", "model.layers.48.input_layernorm.weight": "model-00033-of-00058.safetensors", "model.layers.44.input_layernorm.weight": "model-00033-of-00058.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00034-of-00058.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00034-of-00058.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00034-of-00058.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00034-of-00058.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00035-of-00058.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00035-of-00058.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00035-of-00058.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00035-of-00058.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00035-of-00058.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00035-of-00058.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00035-of-00058.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00035-of-00058.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00035-of-00058.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00035-of-00058.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00035-of-00058.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00035-of-00058.safetensors", "model.layers.49.input_layernorm.weight": "model-00035-of-00058.safetensors", "model.layers.45.input_layernorm.weight": "model-00035-of-00058.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00036-of-00058.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00036-of-00058.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00036-of-00058.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00036-of-00058.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00037-of-00058.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00037-of-00058.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00037-of-00058.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00037-of-00058.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00037-of-00058.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00037-of-00058.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00037-of-00058.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00037-of-00058.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00037-of-00058.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00037-of-00058.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00037-of-00058.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00037-of-00058.safetensors", "model.layers.50.input_layernorm.weight": "model-00037-of-00058.safetensors", "model.layers.46.input_layernorm.weight": "model-00037-of-00058.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00038-of-00058.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00038-of-00058.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00038-of-00058.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00038-of-00058.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00039-of-00058.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00039-of-00058.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00039-of-00058.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00039-of-00058.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00039-of-00058.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00039-of-00058.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00039-of-00058.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00039-of-00058.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00039-of-00058.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00039-of-00058.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00039-of-00058.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00039-of-00058.safetensors", "model.layers.51.input_layernorm.weight": "model-00039-of-00058.safetensors", "model.layers.47.input_layernorm.weight": "model-00039-of-00058.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00040-of-00058.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00040-of-00058.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00040-of-00058.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00040-of-00058.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00041-of-00058.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00041-of-00058.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00041-of-00058.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00041-of-00058.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00041-of-00058.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00041-of-00058.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00041-of-00058.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00041-of-00058.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00041-of-00058.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00041-of-00058.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00041-of-00058.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00041-of-00058.safetensors", "model.layers.52.input_layernorm.weight": "model-00041-of-00058.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00042-of-00058.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00042-of-00058.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00042-of-00058.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00042-of-00058.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00042-of-00058.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00042-of-00058.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00042-of-00058.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00042-of-00058.safetensors", "model.layers.53.input_layernorm.weight": "model-00042-of-00058.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00043-of-00058.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00043-of-00058.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00043-of-00058.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00043-of-00058.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00043-of-00058.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00043-of-00058.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00043-of-00058.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00043-of-00058.safetensors", "model.layers.3.input_layernorm.weight": "model-00043-of-00058.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00044-of-00058.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00044-of-00058.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00044-of-00058.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00044-of-00058.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00044-of-00058.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00044-of-00058.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00044-of-00058.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00044-of-00058.safetensors", "model.layers.54.input_layernorm.weight": "model-00044-of-00058.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00045-of-00058.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00045-of-00058.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00045-of-00058.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00045-of-00058.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00045-of-00058.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00045-of-00058.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00045-of-00058.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00045-of-00058.safetensors", "model.layers.55.input_layernorm.weight": "model-00045-of-00058.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00046-of-00058.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00046-of-00058.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00046-of-00058.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00046-of-00058.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00046-of-00058.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00046-of-00058.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00046-of-00058.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00046-of-00058.safetensors", "model.layers.8.input_layernorm.weight": "model-00046-of-00058.safetensors", "model.layers.4.input_layernorm.weight": "model-00046-of-00058.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00047-of-00058.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00047-of-00058.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00047-of-00058.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00047-of-00058.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00048-of-00058.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00048-of-00058.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00048-of-00058.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00048-of-00058.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00048-of-00058.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00048-of-00058.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00048-of-00058.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00048-of-00058.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00048-of-00058.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00048-of-00058.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00048-of-00058.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00048-of-00058.safetensors", "model.layers.9.input_layernorm.weight": "model-00048-of-00058.safetensors", "model.layers.5.input_layernorm.weight": "model-00048-of-00058.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00049-of-00058.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00049-of-00058.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00049-of-00058.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00049-of-00058.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00050-of-00058.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00050-of-00058.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00050-of-00058.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00050-of-00058.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00050-of-00058.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00050-of-00058.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00050-of-00058.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00050-of-00058.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00050-of-00058.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00050-of-00058.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00050-of-00058.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00050-of-00058.safetensors", "model.layers.10.input_layernorm.weight": "model-00050-of-00058.safetensors", "model.layers.6.input_layernorm.weight": "model-00050-of-00058.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00051-of-00058.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00051-of-00058.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00051-of-00058.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00051-of-00058.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00052-of-00058.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00052-of-00058.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00052-of-00058.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00052-of-00058.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00052-of-00058.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00052-of-00058.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00052-of-00058.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00052-of-00058.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00052-of-00058.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00052-of-00058.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00052-of-00058.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00052-of-00058.safetensors", "model.layers.11.input_layernorm.weight": "model-00052-of-00058.safetensors", "model.layers.7.input_layernorm.weight": "model-00052-of-00058.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00053-of-00058.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00053-of-00058.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00053-of-00058.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00053-of-00058.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00054-of-00058.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00054-of-00058.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00054-of-00058.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00054-of-00058.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00054-of-00058.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00054-of-00058.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00054-of-00058.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00054-of-00058.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00054-of-00058.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00054-of-00058.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00054-of-00058.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00054-of-00058.safetensors", "model.layers.16.input_layernorm.weight": "model-00054-of-00058.safetensors", "model.layers.12.input_layernorm.weight": "model-00054-of-00058.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00055-of-00058.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00055-of-00058.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00055-of-00058.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00055-of-00058.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00056-of-00058.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00056-of-00058.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00056-of-00058.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00056-of-00058.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00056-of-00058.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00056-of-00058.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00056-of-00058.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00056-of-00058.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00056-of-00058.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00056-of-00058.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00056-of-00058.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00056-of-00058.safetensors", "model.layers.17.input_layernorm.weight": "model-00056-of-00058.safetensors", "model.layers.13.input_layernorm.weight": "model-00056-of-00058.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00057-of-00058.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00057-of-00058.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00057-of-00058.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00057-of-00058.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00058-of-00058.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00058-of-00058.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00058-of-00058.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00058-of-00058.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00058-of-00058.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00058-of-00058.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00058-of-00058.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00058-of-00058.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00058-of-00058.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00058-of-00058.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00058-of-00058.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00058-of-00058.safetensors", "model.norm.weight": "model-00058-of-00058.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..e5b39b6305d89284b04934011c68dbb26bf588ca --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5ec79f4207b0e00afb10a7dc0a3e0d4fd91f8acd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 2048, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}