Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/fsx/home/hanze/EM-CoT/verl/checkpoints/em-raft/Qwen2.5-Math-7B-raft-plusplus-numina_math_em-sample1n32-sample32-filter1.0-insufficient0.0-a0.001-b2.0-iter3/global_step_5//actor/huggingface",
+  "_name_or_path": "/fsx/home/hanze/EM-CoT/verl/checkpoints/em-raft/Qwen2.5-Math-7B-raft-plusplus-numina_math_em-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter3/global_step_5//actor/huggingface",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:510cff1f0127ea3aba16dd97d0f44610f1979cf66a9c50117f8e8a864f63016c
-size 4877614880
+oid sha256:fe7e37fa8e22574aaa005ac5b57afd0e49dacbe2bb1b61f49f66dfb8bcf04bd9
+size 4932746000

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1547adadb0c71790eb13905fda708220279a2856554115ea473f846571c239dc
-size 4995129576
+oid sha256:a053e94b697b2bf27bd04104db3e64dfbdf7b1a81c8e189bb2afea2a14d1cab4
+size 4892406456

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3b15a94de7dd45ac1084c4a322c0bf562341f1a9a56d5072e9526f7d490d7e
-size 4885054528
+oid sha256:2b9285a05050e3d48010c8c2b9780ab0908b0a8e09947766a3bc0ac204a0dea0
+size 4973055936

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d68d638928a12393ecb2d1b091b1f5129e0e693923264ecc7190f8472a1f87
-size 473472888
+oid sha256:4548869e93fb63243c7ec5d48e8cbe54c1f57af2a405a4a428e1ec97729ec278
+size 433063512

model.safetensors.index.json

@@ -4,341 +4,341 @@
   },
   "weight_map": {
     "lm_head.weight": "model-00001-of-00004.safetensors",
-    "model.embed_tokens.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.norm.weight": "model-00003-of-00004.safetensors"