Upload model

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/mnt/workspace/14b",
+  "architectures": [
+    "Qwen2Model"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f549c49bde5566c4c7698d941616cb6be9bc96432c0b4643f5ae23379f1681c0
+size 4750149864

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71697a38bdeb5832354e645d9a1ef946ea76900322885b77bcb8ad71efc3f865
+size 4970575328

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f50b564f40e2a118dfe20b86bd162087c5738cd9f6064d625fa5f06ca93dfe0
+size 4939106192

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2085d9b6ec66dd7cf3f72f9fefca62d19f8eb8084a137f2093cbc4ab8a806980
+size 4970575376

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9b0f3ff063e78afd4916ad97e863320a03d69e63decf5e13e207431052b8ae
+size 4939106232

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1a4d8ad8f242e1a228dbc5f65bd7e736211a5e554f8ff74e9ce92770298c8f
+size 4970575376

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c7120ce3ec673ee7128a7f89530c40b4a41ef0658744978a0cfa3fd4f08be3
+size 4939106232

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88848862607b1ae35df82a7b30809bf49633b0e7a0092987c7a346e9d837cb71
+size 4970575376

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d467ff4666ba9742234aadcb75647096927614aa3b1f7f3e405e199b811b14e4
+size 4939106232

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0ee35c9f22d8ac7d491e5181ffe4d3be2c9f4e963acc8f4acd42e92c64571a
+size 4970575376

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf26c92a372f6baae77ae68a37631a1353bc9ee133b1b09f8a9f3b16219e05a
+size 4939106232

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508342cb0488c978d9ff35e30c39822a6dd84e702b975250ac951c614daa0746
+size 1667368744

model.safetensors.index.json

@@ -0,0 +1,585 @@
+{
+  "metadata": {
+    "total_size": 55965863936
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "layers.15.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.16.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.19.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.20.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "layers.24.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.28.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.28.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.28.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.28.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "layers.29.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.29.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.29.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.29.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.30.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.30.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.30.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.30.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.31.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.31.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.31.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "layers.32.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.32.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.32.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "layers.33.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "layers.33.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.33.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.33.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.34.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "layers.34.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.34.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.34.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "layers.35.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.35.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.35.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "layers.36.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.36.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.36.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.37.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.37.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.37.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.37.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "layers.38.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.38.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.38.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.38.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.39.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.39.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.39.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.39.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.40.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.40.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.40.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.40.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.40.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.40.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.41.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.41.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.41.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "layers.41.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.41.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.41.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "layers.42.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "layers.42.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.42.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.42.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.42.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "layers.42.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.42.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.42.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.42.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.42.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.42.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.42.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.43.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "layers.43.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.43.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.43.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "layers.43.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.43.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.43.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.43.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.43.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.43.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "layers.44.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.44.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.44.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "layers.45.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.45.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.45.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.46.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "layers.46.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.46.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.46.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "layers.46.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.46.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.46.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "layers.47.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "layers.47.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.47.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.47.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.47.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "layers.47.self_attn.k_proj.bias": "model-00012-of-00012.safetensors",
+    "layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.47.self_attn.q_proj.bias": "model-00012-of-00012.safetensors",
+    "layers.47.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.47.self_attn.v_proj.bias": "model-00012-of-00012.safetensors",
+    "layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "norm.weight": "model-00012-of-00012.safetensors"
+  }
+}