Upload Qwen2ForSequenceClassification

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/lfs/guestrin-hgx-1/0/merty/Qwen/Qwen2.5-Math-7B-Attempt2",
   "architectures": [
-    "Qwen2Model"
+    "Qwen2ForSequenceClassification"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e813375566d03751fd46d86ccd040635ed6dadde2cb470acc650d84f2325371
-size 4976686992
+oid sha256:31e23e652b3cd0b6a5ab3a43fd7b5e2ead1d234dbc2439c004eaccadd73397f1
+size 4976687216

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164fbca8044229d6bf4149068cb6a17b814c4b9ff3cd732616273df035a096b0
-size 4778621952
+oid sha256:62e6acbba5d4b6e9bdde9fb29f93cb3fbcdc8e3a1c0f2435f9ac3a7369b85db4
+size 4778622352

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71c0f7024bc0a29ddbb9b412e3a9554441df07c720c4e0e0d1b798a7881a0f1d
-size 4932743600
+oid sha256:164b08efa0a7727f3009ce97b14314b6d1b7720bf58b845cedac4bdbffdba0df
+size 4932743960

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d317433abd7c55cd89611ece7f4d52d53dc9a5799ea958f7b45fda5970dacd
-size 4932743624
+oid sha256:c07ba7da8ed809d8aa49cf7f06ff4859ba0dd7fd630f2a077c8ea79eaed2cf62
+size 4932743992

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58acb9e9f53a666dffdffb3c811cba327b07cfd614f46cb75e98a24485855620
-size 4998851880
+oid sha256:3266c74f8a31096f6d6412a2ca864a04bcb182460fe45269fd281e72929bee03
+size 4998852296

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9918af11c08a9bd3585cbffc77b471b5af8e4b61adc1c4e764e9cb6598cb60
-size 3662864928
+oid sha256:60a43181011d06dfcc13af79979dd1e8f4b7f21ff3488eb0668cf4b73af0ec23
+size 3662879608

model.safetensors.index.json

@@ -1,345 +1,346 @@
 {
   "metadata": {
-    "total_size": 28282476544
+    "total_size": 28282490880
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.10.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.10.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.10.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.13.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.14.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.14.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.14.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.15.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.15.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.15.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.16.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.18.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.19.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.19.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.19.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.20.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.20.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.20.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.21.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.21.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.21.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.22.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.24.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.24.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.25.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.25.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.25.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.26.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.26.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.26.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.26.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.27.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.27.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.27.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.3.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.3.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.3.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.4.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.4.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.4.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.9.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.9.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.9.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "norm.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_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.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.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_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_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.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.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-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_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.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.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-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_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-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_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.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.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors",
+    "score.weight": "model-00006-of-00006.safetensors"
   }
 }