Duplicate from loubnabnl/CodeLlama-70b-Instruct-hf

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 32016
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.1"
+}

pytorch_model-00001-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555c88c89d64f969f2f3c62430916e3fb76802c41ae286bd315bdb3e184d9c83
+size 4718928338

pytorch_model-00002-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a069f184aab63ce3f116ba8383612267c46f92ef63453fdb4f97599e66246ccd
+size 4664173598

pytorch_model-00003-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba8ffc01c22f824bde38a20ee1daf28ec730fc1afd6875671f5e8d0f499e1edb
+size 4999717966

pytorch_model-00004-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d5d5285d0e2b80c49611cc9374e2715638b0cda9048222bcdf040165e9ae0f
+size 4966162946

pytorch_model-00005-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a1562e34afffe1940f191a3eeb2b557b284aff4880cece439487b35ea4a45d
+size 4664140254

pytorch_model-00006-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603c8dec52370bac4ca1ecdb5625a13b9603c5a20198181241a1fe943d1063b1
+size 4664173662

pytorch_model-00007-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b634b279e3a8579110a8c7509fe813965900afaa4aaaf4d0139b01e2d7818a83
+size 4664173662

pytorch_model-00008-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d20d25cf37021ff5572b1906b37e356f8cdbba772d40a0eeda8ffb0ac27f73
+size 4999718030

pytorch_model-00009-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e3697c38982fdb0c56e6e022a215a3e6673c5d073ce8b6c4b91e3369608c50
+size 4966162946

pytorch_model-00010-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea49cca3be9c5b5235e59aa4eef8edbbd6f86414e6acf667431e68206ce250b9
+size 4664140254

pytorch_model-00011-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9905f1df7c725cede45b212c801c2820410375d3c145626b1cd3bcc0388b7b
+size 4664173662

pytorch_model-00012-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254723a6b37a0a194bb5256898897b6ab594b61d1fd60b932565f6d7e73a7fc4
+size 4664173662

pytorch_model-00013-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8e96cad83972c1153dddcf455d13378ffcc5efdee0ae32af62ae917e59f4d8
+size 4999718030

pytorch_model-00014-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97ce45487202b5d455a22121a137d194501872576d1c97bab50519eb6672875
+size 4966162946

pytorch_model-00015-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f924e79868a6bab5eeac6b9f12d7f74eb6f122a20b1ac2df9a11433982449ba
+size 4664140254

pytorch_model-00016-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f571c8016711bee8c0eeb2741e2730d9032c0eefef343e895e376e8b39a6be
+size 4664173662

pytorch_model-00017-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4040e65d15558b0c09e62fdf7a80e5d1ce6b3ae54ccda4086a903053b44df9
+size 4664173662

pytorch_model-00018-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f77aff8e2049f07c114ef246f25b2dce28217dad6dbb85afbabfe8b31d00207
+size 4999718030

pytorch_model-00019-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9505ab17ebe35c84208ff27ddd424f017db272864c43d8b31a5bc012381ff3b5
+size 4966162946

pytorch_model-00020-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e74de256316e0415034b81d739a3d0c3404c06188f78cd7f14d3893206b215d
+size 4664140254

pytorch_model-00021-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dafd09f3237a55064e79d73549538794dc0059e8fd7e604f368f5849457a62cf
+size 4664173662

pytorch_model-00022-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963968112411bffc3d1c9f3ae7573b73f1032d9ee8b1b60b22bc8bc219fde903
+size 4664173662

pytorch_model-00023-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121a2abc33a183fd8d4a65280228af09d277a79b04dd0369c7a6b8f85e23569b
+size 4999718030

pytorch_model-00024-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b6119c0fbe0410f519021487f51a7526b2b51aa152a567735e8934bd22f271
+size 4966162946

pytorch_model-00025-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2a306b9dc55a03ca0f250bc25cc9e0c87aea0b8e352fd3e5517e9d021917b0
+size 4664140254

pytorch_model-00026-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d195d8b4bf3e4b4fe266cc55a3ff2a8b1337f9f808108e637dd21254b83be368
+size 4664173662

pytorch_model-00027-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06df3e01915ad034b7e62658e159e6e2c87b5f12643676a38ea58e772cacd78f
+size 4664173662

pytorch_model-00028-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856d7a5d32b3d227bdf3eb2dd7d43911af33f4be14ba7f7a6a0f027adaf3e226
+size 4999718030

pytorch_model-00029-of-00029.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd33e71be1522707b2a70db7f7aa608166f89ae4f9e26037358165c7bfd40a7
+size 3910555868

pytorch_model.bin.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 137953820672
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00029-of-00029.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.60.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.61.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
+    "model.layers.62.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.64.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
+    "model.layers.65.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
+    "model.layers.67.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.69.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.70.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.72.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
+    "model.layers.73.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.75.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
+    "model.layers.76.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.78.input_layernorm.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.mlp.down_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.mlp.up_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
+    "model.layers.79.input_layernorm.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.mlp.down_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.mlp.up_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00029-of-00029.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
+    "model.norm.weight": "pytorch_model-00029-of-00029.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99049b351301fb75b3b0587a484b675cbfd51abe27d2b92eabd385e4c41f97e9
+size 500033

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}