Upload folder using huggingface_hub (#1)

- 6c6e4f85c5cd9b80202456cc5890f7bd912abfefc211b5b149730f8bbc2ea904 (c37757c82dc57b461817d72a226ebece8766fb30)
- 7884bf4fff7955167aacba4dbaa6960f6d5e293ced444608aa0f11d6f9df673b (babf493cd059a563cd0c1a8785ae756de0a2a7bc)
- 3db8ba1eb8ec53cb60e9f5894f27e2883bfb09c04e7ae91df9c84c88420a261c (6c5218649f1703729f118bd999b92da128e7d051)
- 0fb0c1b84b8635fd3cd1ff0d72c4e97d49b3989f7ae59bbaf2f5a464947a962d (0a02a959708a4a91f0b3f54d37a5f798b04f2b17)
- ba9e0244c01bb1738a135d699139428bb8e459f6f063297d7a8be460f37bac3a (870d314703de99b40cf377440120d42f9ae7f591)
- 0f95e182f8bf5ee9a0ae9c5510331d2d7cb9edf6dec4ab0a4d392c1c16d8bf94 (aeebea2ded7a3d6c56539deff7879d4671173d66)
- 4211f46be2ef29dec330d4d57a63731597a34993034800149176df1cced38d31 (085568a4647a640cd4900b18df303ba5cc15ae5a)
- 0fdd0ae5b0d4cf1fd9fb1155bce962870c7d5cfe4b0f6a98ece05ce750130b6f (5330955d821ff4385cd8c8ee1580c228669e57de)
- e81aac101e22fbccca19d47fbcadc7f1ea42296576dd169a4d3cde7dea8607f0 (1359bdab63530ec2db4d5a424646bc6380b13e31)
- cb76ce597f5383d4b288c2c0fc5f70280e6b60080d449afb7819d1f85e1264db (11aaace23957c36149270747b73d04549ab15b8c)
- 3549ffbe4a90d1d6db88f939aab67effbc0d36d82f5d1a4b946e592032265b4f (2db5df389e9c78de0c642b95069e86a6f1e0e19e)
- ea293ffca4d449073d6b3bf5c249b02adeb263e46a783adec5e5ce721b0f4ef9 (0a45ae072139626eeade28784abc02e686984223)
- 9e8eef09bb5d2502322aad2f2c3b616b0b7ae55f5466809005a5d40bc26cb7fb (6892e6b1df8d5c2ade0d9557953a74de599bd034)
- d00672b18dcef0c51ba0c42648a8fde7ba952e271420cea8b6b5585544256ee7 (318a0856fd50e46d65e502ed66d9c5f57fe72950)

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "'<eod>'": 39410,
+  "<bot>": 39409,
+  "<human>": 39408
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "swish",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "use_bfloat16": true,
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 39424,
+  "rope_scaling": {"type": "linear", "factor": 2.0}
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f16119fedc5b881cb0838c5c2d4504c0ca0aa88b298f3a23833d0f8c856998c
+size 896534991

pytorch_model-00002-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba227aacafbfc10315481d684a2d94af405e80bb193daa01965d4df901c0edf9
+size 985707823

pytorch_model-00003-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4dccf59fd82c9a619f8201c67a2d946f7e655393cc404c58af0a8573a6603c
+size 917528001

pytorch_model-00004-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54686aceedc0d9bca0c022251a283458b9b969804753c2dd771c5f146b6b8a33
+size 985707823

pytorch_model-00005-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bda0e40b8b66be4d5f8501b946e92fb5443cde4c98df34a25bcd44d785d21d7
+size 917528001

pytorch_model-00006-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7773b93cb9bdbfbaf6c6bcc8a43a17623f9583294a166fae4d900acc8dd583c2
+size 985707823

pytorch_model-00007-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a552af85bd188c1bc86fc06835188117f9d3edc78813bd8335b96b3333f35cac
+size 917528001

pytorch_model-00008-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022b30c1fe2f96b9c432ff13f4ad377e9a091a4bcb5caadbdc94fe32c65843ea
+size 985707823

pytorch_model-00009-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d90ae5f7b7745bea55d851299975c4c2e46a349b51ecda82c0da2d46ac7ce7
+size 917528001

pytorch_model-00010-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3647a5205a54faf24f07dc45d488bc79180904cfca0c9a5a85b7095a6d3a09ac
+size 985707823

pytorch_model-00011-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0723e13c62a874e62d223244f32496f6452fced82695d4d61aa103464a785f42
+size 917528001

pytorch_model-00012-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b84f155bbf8f2f43f03ef47c4f7d13ffd453c241d7c2f23b2d1cf3eb3931dc
+size 985707823

pytorch_model-00013-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e622f42d6a1b82dedd17a21f75bc3dc2eb7f0a19ed7432248465681be972d5
+size 917528001

pytorch_model-00014-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6264b4ed82487fadce3f3a3493f4967f2b1e4f4191b03072d141f1a2a2fca45f
+size 985707823

pytorch_model-00015-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e750f7842797725fc9ec8526a38060d77682fcfcd6b8bddd6c139d9575514bc
+size 917528001

pytorch_model-00016-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654cf4b2f7ee83bb5aa213e2de1918aa33ccada4b9b35ba715a62a01c6a8144f
+size 985707823

pytorch_model-00017-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f560651ce1f0c1353910d560643be0628502ea4cd7b74d559a447e893572e6ae
+size 917528001

pytorch_model-00018-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5205a889bed8f03cd6251cad6a69519f9c7b3ea6cd614678fcbcdca991385e0d
+size 985707823

pytorch_model-00019-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859840b597f18cd884dd4f30c605afd693c6404fbb7e8a7d4917a2708e90b2d0
+size 917528001

pytorch_model-00020-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f56fa516bd547bc99a984d97e6ced680e06d3710b523733b84768addedd6236
+size 985707823

pytorch_model-00021-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba2e822d4c63cbfd5e6056a48250266af3c25d11c7778b3323cb399f1a1d9607
+size 917528001

pytorch_model-00022-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b45e3b7e0e5348720e6e231e2e0885da6485b3f7e70eba9050935a0fa62853
+size 985707823

pytorch_model-00023-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee07ac5f730103fb34b4e078b01ad4b2cfa6a259457095f90f1ba7c27f538a1
+size 917528001

pytorch_model-00024-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd22cd0c0b628ff7d906f24caf70f3dd18ffb8d44bcdf158e71c100dff80e6ae
+size 985707823

pytorch_model-00025-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4760754f86b794913d5f8abe8570dae93941094c43f9b9a3bce75ebe7b689d7e
+size 917528001

pytorch_model-00026-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898e45f6f6159b038013e47d75343bbbd281aedcdd7195f3786f37289cc823aa
+size 985707823

pytorch_model-00027-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352b8335da8f8432a64a2977ab9ff0e8c8be3527a8e1dbabf9e5b1b9c2855be3
+size 917528001

pytorch_model-00028-of-00028.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ec32f4472f7c89eaeca67d8d1edc65fa40637a0ccd048f403c838b3289495c
+size 545291867

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 26183777280
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00028-of-00028.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00028.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00028.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00028.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00028.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00028.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00028.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00028.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00028.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00028.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00028.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00028.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00028.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009-of-00028.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00028.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00028.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00010-of-00028.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00028.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011-of-00028.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00028.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00028.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00012-of-00028.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00028.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013-of-00028.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00028.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00028.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00028.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00028.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00014-of-00028.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00028.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00015-of-00028.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00028.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00028.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00016-of-00028.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00028.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00017-of-00028.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00028.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00028.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00018-of-00028.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00028.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00019-of-00028.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00028.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00028.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00020-of-00028.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00028.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00028.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00028.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00021-of-00028.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00028.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00028.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00022-of-00028.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00028.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00023-of-00028.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00028.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00028.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00024-of-00028.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00028.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00025-of-00028.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00028.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00028.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00026-of-00028.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00028-of-00028.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00028-of-00028.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00028-of-00028.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00028.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00027-of-00028.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00028.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00028.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00028.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00028.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00028.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00028.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00028.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006-of-00028.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00028.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00028.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00028.bin",
+    "model.norm.weight": "pytorch_model-00028-of-00028.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<human>",
+    "<bot>",
+    "'<eod>'"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd7e445833dd0889206aba242c2a51ecbae2437fd328d1759a35475fd8c0423
+size 588619

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}