Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.8,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b195eb69607c01e8f6d252b917100dafa323849de05bb4c0fb28090cd6a0b49c
+size 3833644176

model-00002-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b3c05f339b1e439c0b840c762f5493db3ff97b3af73da5edcca0624c7b998d
+size 3892513824

model-00003-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99f356a786cf1fa021a225e3c97bc7cf4212b94c47b95cda12620b2eaff1682
+size 3892530552

model-00004-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da4fad5b26ad86345bd42af839d26b780468a9e04ce039bad67848fdeddb78d
+size 3624045376

model-00005-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7a27999069e41a3e05eef4b9fb3c73cbf982da725f9bded74babe68286a67f
+size 3892480832

model-00006-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7918017b33535e9590fad615df8fb4cf3a599d844edbb75d5dd89becfaa8964d
+size 3892480848

model-00007-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494ace12c66c6d1d8eb5bf63afdc91398d19b977129cf756cd2a2d5e4b50eccf
+size 3892513856

model-00008-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d5366ce21ce13de8fd45ecfd89d777a0fe26c6d3fe92324ebd8266db14375f
+size 3892530576

model-00009-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7194085c6f9286478d683351da843bf23de9170b152632412f562b6fbfbed3bb
+size 3624045400

model-00010-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8136d21c8c27339208ec92fe17dde56ef2e01393518566ad3f4958cf6bbbedc4
+size 3892480856

model-00011-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003081145a7a7cf8a8c18a6439c3c62b140f65f51c81eb61a5324cb167f7a825
+size 3892480848

model-00012-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42944464f6079b6200333ce7567a22fdfa21165a8d080be071360d2a204ddd01
+size 3892513856

model-00013-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:128e13d29cbea3f50269b7beb969d6b7868277a9ee3ba07d9d946edc7410fb29
+size 3892530576

model-00014-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00dfa2cb6582ceb76aaa9c7ed9bcbd7a252343e2821624ad5df2348ae65806c7
+size 3624045400

model-00015-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484b9ee0552ce125fbc60a439b0b36dd9447d79fe249cbd9a4056b35f56045f8
+size 3892480856

model-00016-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64e27c6761bcbea956f8d11b96b291cb3dadc2b62d9ab65d30b8289dbb158ae
+size 3892480848

model-00017-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334527a89f01f4dc512f192ae671cf4ba2a3810e0ccc79fa43299ead140bb96f
+size 3892513856

model-00018-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5be36f95bd5846b89f918a2a053d840d9b330fe0c8d8d79cde35eecc48e7c1
+size 3892530576

model-00019-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495658f939af7b15f1eae23cf8e3befb29f35657bef2a750d1616a9f9c6a2739
+size 3624045400

model-00020-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41168f2338ebdb0f4adc231291e5b14aa14ffec403e0e4cfbe8d472b8ccecedb
+size 3892480856

model-00021-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e0b33cb8d8878b1a0818766dc28c59504de8f9c657d80af5548993ff1e17d
+size 3892480848

model-00022-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1950dd29c3e419908aa14ca874ba0039cc3eaad43b77317c83f01569b5f6f8f
+size 3892513856

model-00023-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9470c234f3aa2dff524906ec4215207ab1afc4607456068850a9010badae47fb
+size 3892530576

model-00024-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a802003dbe0927336e9af989606608e3dd5139019b79bef924189aaf91cc9d
+size 3624045400

model-00025-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66cd27a05f98cbae1e626b9ff02ba19c399f390351655a63b5147f40a66cfdad
+size 3892480856

model-00026-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4dd446ea1efb07d9dae378d8c7a7d7142f05bed36b12e6ed6869ab82853163a
+size 3892480848

model-00027-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1c855a9d854c2cc95981c7a98ba1d44e2409850a441192e6ed8a44c98421bc
+size 3892513856

model-00028-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3490fa50b265d1ec8b1ea4f386812864cbe0488dd730e9266f64845e4595d5
+size 3892530576

model-00029-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3727dcae3d37bfa35c404c5894e3af1b1130826c1b585c95356fd81c45435026
+size 3624045400

model-00030-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5599e044450a9f4057eb97de3e00c49e8d54dc39085b09cee9dddcbd5cb7d32
+size 3892480856

model-00031-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a30bff1fad465bb48ef26111e84ed99838050d58061214a408530647981fc18
+size 3892480848

model-00032-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a95d84ed75b9895c11132afc6caa6bb8499651243b35bcae34bd80b3831c1ba
+size 3892513856

model-00033-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64c4d2d6b022b571aae97c14e9179ce28b8b1f90528b1f721d24741d29ee726
+size 3892530576

model-00034-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43eb50a8fc6f0dd4cffdddf462fb08aee5a444954f0f4957dc9c0da70b9cf92
+size 3624045400

model-00035-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a30c9174413ab917a22b6526695889c9393e1eb699923830ed3e575b5f4da3
+size 3892480856

model-00036-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59378b211d95eb2e7bec686d625ba9dd25ede452408c498aa25761a3842bc54a
+size 3892480848

model-00037-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e8af4359ad4ece8eff4fe72c1c8418fb1e27504d3c9227c2694256a25b0b6b
+size 3892530328

model-00038-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65524062eb101007c956c309e21d02de7f6e48bac2338d72a827f433d57353d
+size 2491416704

model.safetensors.index.json

@@ -0,0 +1,970 @@
+{
+  "metadata": {
+    "total_size": 144575840256
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00038-of-00038.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00038.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00038.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00038.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00038.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00038.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00038.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00038.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00038.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00038.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00038.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00038.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00038.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00038.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00038.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00038.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00038.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00038.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00038.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00038.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00006-of-00038.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00006-of-00038.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00006-of-00038.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00038.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00038.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00038.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00038.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00038.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00038.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00038.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00038.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00038.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00038.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00038.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00038.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00038.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00038.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00038.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00038.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00038.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00038.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00008-of-00038.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00038.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00038.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00038.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00009-of-00038.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00009-of-00038.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00009-of-00038.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00038.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00038.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00009-of-00038.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00009-of-00038.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00009-of-00038.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00038.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00038.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00038.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00010-of-00038.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00010-of-00038.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00010-of-00038.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00038.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00038.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00038.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00038.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00038.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00038.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00011-of-00038.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00038.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00010-of-00038.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00010-of-00038.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00010-of-00038.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00038.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00038.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00038.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00011-of-00038.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00011-of-00038.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00011-of-00038.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00038.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00038.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00011-of-00038.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00011-of-00038.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00011-of-00038.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00038.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00038.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00038.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00012-of-00038.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00012-of-00038.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00012-of-00038.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00012-of-00038.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00012-of-00038.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00012-of-00038.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00038.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00038.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00038.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00038.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00038.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00013-of-00038.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00038.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00038.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00038.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00014-of-00038.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00014-of-00038.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00014-of-00038.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00038.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00038.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00014-of-00038.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00014-of-00038.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00014-of-00038.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00038.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00038.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00038.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00038.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00038.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00015-of-00038.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00015-of-00038.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00015-of-00038.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00016-of-00038.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00038.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00015-of-00038.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00015-of-00038.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00015-of-00038.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00038.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00016-of-00038.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00038.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00016-of-00038.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00016-of-00038.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00016-of-00038.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00017-of-00038.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00017-of-00038.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00016-of-00038.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00016-of-00038.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00016-of-00038.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00038.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00017-of-00038.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00038.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00017-of-00038.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00017-of-00038.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00017-of-00038.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00017-of-00038.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00017-of-00038.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00017-of-00038.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00017-of-00038.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00018-of-00038.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00038.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00019-of-00038.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00019-of-00038.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00018-of-00038.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00018-of-00038.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00019-of-00038.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00019-of-00038.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00019-of-00038.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00019-of-00038.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00019-of-00038.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00038.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00038.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00020-of-00038.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00020-of-00038.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00019-of-00038.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00019-of-00038.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00019-of-00038.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00038.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00020-of-00038.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00020-of-00038.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00020-of-00038.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00020-of-00038.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00020-of-00038.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00021-of-00038.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00021-of-00038.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00020-of-00038.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00020-of-00038.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00020-of-00038.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00020-of-00038.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00021-of-00038.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00021-of-00038.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00021-of-00038.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00021-of-00038.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00021-of-00038.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00022-of-00038.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00022-of-00038.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00021-of-00038.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00021-of-00038.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00021-of-00038.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00021-of-00038.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00022-of-00038.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00022-of-00038.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00022-of-00038.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00022-of-00038.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00022-of-00038.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00022-of-00038.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00022-of-00038.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00022-of-00038.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00022-of-00038.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00023-of-00038.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00023-of-00038.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00024-of-00038.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00024-of-00038.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00023-of-00038.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00023-of-00038.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00038.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00038.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00038.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00038.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00024-of-00038.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00024-of-00038.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00024-of-00038.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00024-of-00038.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00024-of-00038.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00025-of-00038.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00025-of-00038.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00024-of-00038.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00024-of-00038.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00024-of-00038.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00024-of-00038.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00025-of-00038.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00025-of-00038.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00025-of-00038.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00025-of-00038.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00025-of-00038.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00026-of-00038.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00026-of-00038.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00025-of-00038.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00025-of-00038.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00025-of-00038.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00025-of-00038.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00026-of-00038.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00026-of-00038.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00026-of-00038.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00026-of-00038.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00026-of-00038.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00027-of-00038.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00027-of-00038.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00026-of-00038.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00026-of-00038.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00026-of-00038.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00026-of-00038.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00027-of-00038.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00027-of-00038.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00027-of-00038.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00027-of-00038.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00027-of-00038.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00027-of-00038.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00027-of-00038.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00027-of-00038.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00027-of-00038.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00028-of-00038.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00028-of-00038.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00038.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00038.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00038.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00038.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00038.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00029-of-00038.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00029-of-00038.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00028-of-00038.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00028-of-00038.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00029-of-00038.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00029-of-00038.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00029-of-00038.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00029-of-00038.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00029-of-00038.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00030-of-00038.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00030-of-00038.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00029-of-00038.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00029-of-00038.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00029-of-00038.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00029-of-00038.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00030-of-00038.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00030-of-00038.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00030-of-00038.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00030-of-00038.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00030-of-00038.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00031-of-00038.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00031-of-00038.safetensors",
+    "model.layers.64.self_attn.k_proj.bias": "model-00030-of-00038.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.64.self_attn.q_proj.bias": "model-00030-of-00038.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.64.self_attn.v_proj.bias": "model-00030-of-00038.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00030-of-00038.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00031-of-00038.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00031-of-00038.safetensors",
+    "model.layers.65.self_attn.k_proj.bias": "model-00031-of-00038.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.65.self_attn.q_proj.bias": "model-00031-of-00038.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.65.self_attn.v_proj.bias": "model-00031-of-00038.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00032-of-00038.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00032-of-00038.safetensors",
+    "model.layers.66.self_attn.k_proj.bias": "model-00031-of-00038.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.66.self_attn.q_proj.bias": "model-00031-of-00038.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.66.self_attn.v_proj.bias": "model-00031-of-00038.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00038.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00032-of-00038.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00032-of-00038.safetensors",
+    "model.layers.67.self_attn.k_proj.bias": "model-00032-of-00038.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.67.self_attn.q_proj.bias": "model-00032-of-00038.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.67.self_attn.v_proj.bias": "model-00032-of-00038.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.self_attn.k_proj.bias": "model-00032-of-00038.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.self_attn.q_proj.bias": "model-00032-of-00038.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.68.self_attn.v_proj.bias": "model-00032-of-00038.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00032-of-00038.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00033-of-00038.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00033-of-00038.safetensors",
+    "model.layers.69.self_attn.k_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.69.self_attn.q_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.69.self_attn.v_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00038.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00038.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00038.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00038.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00038.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00038.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00033-of-00038.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00038.safetensors",
+    "model.layers.70.self_attn.k_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.70.self_attn.q_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.70.self_attn.v_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00034-of-00038.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00034-of-00038.safetensors",
+    "model.layers.71.self_attn.k_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.71.self_attn.q_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.71.self_attn.v_proj.bias": "model-00033-of-00038.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00033-of-00038.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00034-of-00038.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00034-of-00038.safetensors",
+    "model.layers.72.self_attn.k_proj.bias": "model-00034-of-00038.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.72.self_attn.q_proj.bias": "model-00034-of-00038.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.72.self_attn.v_proj.bias": "model-00034-of-00038.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00035-of-00038.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00035-of-00038.safetensors",
+    "model.layers.73.self_attn.k_proj.bias": "model-00034-of-00038.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.73.self_attn.q_proj.bias": "model-00034-of-00038.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.73.self_attn.v_proj.bias": "model-00034-of-00038.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00034-of-00038.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00035-of-00038.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00035-of-00038.safetensors",
+    "model.layers.74.self_attn.k_proj.bias": "model-00035-of-00038.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.74.self_attn.q_proj.bias": "model-00035-of-00038.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.74.self_attn.v_proj.bias": "model-00035-of-00038.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00036-of-00038.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00036-of-00038.safetensors",
+    "model.layers.75.self_attn.k_proj.bias": "model-00035-of-00038.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.75.self_attn.q_proj.bias": "model-00035-of-00038.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.75.self_attn.v_proj.bias": "model-00035-of-00038.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00035-of-00038.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00036-of-00038.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00036-of-00038.safetensors",
+    "model.layers.76.self_attn.k_proj.bias": "model-00036-of-00038.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.76.self_attn.q_proj.bias": "model-00036-of-00038.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.76.self_attn.v_proj.bias": "model-00036-of-00038.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00037-of-00038.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00037-of-00038.safetensors",
+    "model.layers.77.self_attn.k_proj.bias": "model-00036-of-00038.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.77.self_attn.q_proj.bias": "model-00036-of-00038.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.77.self_attn.v_proj.bias": "model-00036-of-00038.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00036-of-00038.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00037-of-00038.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00037-of-00038.safetensors",
+    "model.layers.78.self_attn.k_proj.bias": "model-00037-of-00038.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.78.self_attn.q_proj.bias": "model-00037-of-00038.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.78.self_attn.v_proj.bias": "model-00037-of-00038.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.self_attn.k_proj.bias": "model-00037-of-00038.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.self_attn.q_proj.bias": "model-00037-of-00038.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.79.self_attn.v_proj.bias": "model-00037-of-00038.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00037-of-00038.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00038.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00038.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00038.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00038.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00038.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00038.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00038.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00038.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00005-of-00038.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00005-of-00038.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00038.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00005-of-00038.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00038.safetensors",
+    "model.norm.weight": "model-00037-of-00038.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}