Upload LlamaForCausalLM

README.md

@@ -1,8 +1,8 @@
 ---
 library_name: transformers
+license: apache-2.0
 tags:
 - llama-factory
-license: apache-2.0
 ---
 
 # Model Card for Model ID

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "beomi/Solar-Ko-Recovery-11B",
+  "_name_or_path": "/home/work/dweax/train/model/solar-ko-recovery-11b-chat-v2",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -23,7 +23,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.42.3",
   "use_cache": true,
   "vocab_size": 64000

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4afc7c8d3c4137fdba32200678a1d13ad49868698139011a282980b2ee6af910
+size 4941026032

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d097196155aebbc8c12f6c4b36300e1f06651e852cc3dfc572b5b3edd58ad9
+size 4999813072

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4dce529b4390943818ee5a622e91c4c0b24edfeb0625a557a6aebbc80144e36
+size 4832007496

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af2d62ca0ea534e19ec61419a37d37e95d64a959206674e807d2b014925add6
+size 4999813120

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70212cc29215d1b821d0b91c06dbcf753ff3cb2207b5857cef14235e9e7ab1a8
+size 4999813128

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9661a816619183e423e22c097ddf41a3bf3f7f88acd3582c8626b2910b4657e5
+size 4832007496

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22e0dffdbce7f22f49953e1c377cd95c0c2c2668cc04be64d89ad2272e137c2
+size 4999813120

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8208218f13536f7461eec8c662029e8fcc44d0ad8456f1f089877139dca5d74
+size 4999813128

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f20c27b90147cfd572d52081b7952301e624e95481abc1a1b8b7d5e1d90428f
+size 4370616144

model.safetensors.index.json

@@ -1,442 +1,442 @@
 {
   "metadata": {
-    "total_size": 21987336192
+    "total_size": 43974672384
   },
   "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-00003-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-00004-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-00004-of-00008.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-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-00005-of-00008.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00005-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-00005-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-00005-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-00005-of-00008.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00005-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-00006-of-00008.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00006-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-00006-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-00006-of-00008.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00006-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-00007-of-00008.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00007-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-00007-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-00007-of-00008.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-    "model.layers.40.self_attn.v_proj.weight": "model-00007-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-00008-of-00008.safetensors",
-    "model.layers.46.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.46.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
-    "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.46.self_attn.v_proj.weight": "model-00008-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-00008-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-00008-of-00008.safetensors",
-    "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
-    "model.layers.47.self_attn.v_proj.weight": "model-00008-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-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
   }
 }