Faro model

README.md

@@ -1,11 +1,11 @@
 ---
+language:
+- zh
+- en
 license: apache-2.0
 datasets:
 - wenbopan/Fusang-v1
 - wenbopan/OpenOrca-zh-20k
-language:
-- zh
-- en
 ---
 
 ![image/webp](https://cdn-uploads.huggingface.co/production/uploads/62cd3a3691d27e60db0698b0/s21sMRxRT56c5t4M15GBP.webp)

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "/cephfs/panwenbo/work/repos/fusang_8x7b/outputs/fi/merged",
+  "_name_or_path": "/cephfs/panwenbo/work/repos/fusang_8x7b/outputs/fi-chatml/merged",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 7,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -22,7 +22,7 @@
   "rope_scaling": null,
   "rope_theta": 10000000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.38.1",
   "use_cache": false,
   "vocab_size": 64000

generation_config.json

@@ -2,7 +2,10 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "do_sample": true,
-  "eos_token_id": 2,
+  "eos_token_id": [
+    2,
+    7
+  ],
   "pad_token_id": 0,
   "transformers_version": "4.38.1"
 }

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017d6ad9bd2b955a289a1eb497089795fb41dcdddf657c52cbbc31a61fd146e6
+size 4932711424

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a518ed252e9fe8a73b1db69d99e8c830f682b5151365c4c006ab0de55dfd378a
+size 4976802816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f91f3e039eabcd8477f458eea00ee8af98a5ced62a68896cca4b3d0555e7cc
+size 4968397360

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46aadaf2c06f0fd9a61caaf799ac29cdc5ca8d9d05452c9944c5549e5844f38c
+size 2780953384

model.safetensors.index.json

@@ -1,442 +1,442 @@
 {
   "metadata": {
-    "total_size": 35317628928
+    "total_size": 17658814464
   },
   "weight_map": {
-    "lm_head.weight": "model-00008-of-00008.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.40.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.40.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.41.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.41.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.input_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.47.input_layernorm.weight": "model-00008-of-00008.safetensors",
-    "model.layers.47.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.47.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
-    "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-    "model.norm.weight": "model-00008-of-00008.safetensors"
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }