Depth Up Scaled The Highest SNR Layers

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": ".\\TroyDoesAI/Mermaid-Contextual-Obedient-RAG-Phi-3-medium-128k-instruct-14B\\",
+  "_name_or_path": ".\\Mermaid-Contextual-Obedient-RAG-Phi-3-20B\\",
   "architectures": [
     "Phi3ForCausalLM"
   ],
@@ -18,7 +18,7 @@
   "max_position_embeddings": 131072,
   "model_type": "phi3",
   "num_attention_heads": 40,
-  "num_hidden_layers": 40,
+  "num_hidden_layers": 54,
   "num_key_value_heads": 10,
   "original_max_position_embeddings": 4096,
   "pad_token_id": null,

generation_config.json

@@ -1,11 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": [
-    32000,
-    32001,
-    32007
-  ],
-  "pad_token_id": 32000,
+  "eos_token_id": 32000,
   "transformers_version": "4.40.2"
 }

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80becca823ff94de6e34479dbaf1658d812f31708f517c378b68e1c5bf9cd5a3
+size 4915982880

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a860338a2eb52c1eb3fb58dda403a364d7923e92414f17c81969f2401e38679
+size 4954690672

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e691dc944af771b5174eb07d2fd9f4d06bf6ceb5ff8f5982e4cfc88c5b9f34
+size 4902241304

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a41b0fba7cbfa02afbb7b310802d657f03c0fd64faf155c16b491a2d2870ed
+size 4771169072

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172c19fa48a968652937d72476e42ad641415b71e938e6cc48fa01f843e779dd
+size 4771169072

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaac99c2fdd1d63140de4ccca78ce9f8322c58ddb398a0eb90e9abbdfc973914
+size 4771169072

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ff2fbc61c7a8a5eb59b5ee61bb67760e58182ef7c9759aef7aa662a8027081
+size 4771169072

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14e7e2b9f6d1d08a2bb97d02745fac3fac7d6dc8d77d56dafa27f0c9e42a00ca
+size 3605251472

model.safetensors.index.json

@@ -1,250 +1,334 @@
 {
   "metadata": {
-    "total_size": 27920476160
+    "total_size": 37462804480
   },
   "weight_map": {
-    "lm_head.weight": "model-00006-of-00006.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.35.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.36.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.36.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
-    "model.norm.weight": "model-00006-of-00006.safetensors"
+    "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_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.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.qkv_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_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.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.qkv_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_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.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00002-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_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.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.qkv_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_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.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.qkv_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_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.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.qkv_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_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.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.qkv_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_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.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00003-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_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.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00003-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_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.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.qkv_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_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.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.qkv_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_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.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.qkv_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_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.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00004-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_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.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00004-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_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.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.qkv_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_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.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.qkv_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_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.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.qkv_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_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.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.qkv_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.mlp.gate_up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.self_attn.qkv_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.34.mlp.gate_up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.34.self_attn.qkv_proj.weight": "model-00005-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_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.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.35.self_attn.qkv_proj.weight": "model-00005-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_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.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.qkv_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_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.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.qkv_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_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.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.qkv_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_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.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.mlp.gate_up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.self_attn.qkv_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.41.mlp.gate_up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.41.self_attn.qkv_proj.weight": "model-00006-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_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.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.42.self_attn.qkv_proj.weight": "model-00006-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_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.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.qkv_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_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.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.qkv_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_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.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.qkv_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_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.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.self_attn.qkv_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.mlp.gate_up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.self_attn.qkv_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.48.mlp.gate_up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.48.self_attn.qkv_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.49.mlp.gate_up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.49.self_attn.qkv_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.50.mlp.gate_up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.50.self_attn.qkv_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.51.mlp.gate_up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.51.self_attn.qkv_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.52.mlp.gate_up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.52.self_attn.qkv_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.53.mlp.gate_up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.53.self_attn.qkv_proj.weight": "model-00008-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_up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-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_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.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.qkv_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_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.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.qkv_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_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.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors"
   }
 }