Upload folder using huggingface_hub

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3cb223e53ec247d7cb42a067d7be755fb3592b1a28ca2e4000ab0b6c1d8aca
-size 4903450720
+oid sha256:636f4464c493afdf0dd9ea59e304ab21afb4a937ffa208217d93e2887d9aa98d
+size 4877733176

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ee07d5990b8378ce80fccbac367da28763bc7155fbd12403d0d90e7ae94128
-size 4092213240
+oid sha256:5af1c69af92756093a5b52a13183fd3d91dfc37ef429ed985138583dca9f2f84
+size 4984073656

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80683dd0cdeac8e1a81e1adc657e41076894fe687720933018e27e3ad5b36557
-size 4995087432
+oid sha256:d3bad185e4f0b01a4b4022b87f4f3df243486b83f8d62631c54df44483839d4a
+size 4932724144

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bcedde595947ba3b8a1bc4fa1694fc43842eaa50c688cfb8318dbf720dd7712
-size 1240520464
+oid sha256:ff3346e44edeb6b46b058949cebb2a3f7205620e555b0e0ccf9cae94f9cb7fd0
+size 436740920

model.safetensors.index.json

@@ -3,344 +3,344 @@
     "total_size": 15231233024
   },
   "weight_map": {
-    "lm_head.weight": "model-00002-of-00004.safetensors",
-    "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "lm_head.weight": "model-00003-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-00003-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-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-00003-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00002-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.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-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-00003-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-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.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-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.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.gate_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-00003-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-00003-of-00004.safetensors",
     "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00001-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-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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-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-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00003-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-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-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-00002-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-00001-of-00004.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00004-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-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-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-00003-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00001-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-00004-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-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-00004-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-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-00004-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-00003-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-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-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-00001-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-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-00004-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-00001-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-00003-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-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.15.self_attn.q_proj.bias": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-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.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-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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.16.self_attn.q_proj.bias": "model-00001-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-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-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-00003-of-00004.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "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.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "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-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00003-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-00001-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00001-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-00004-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.19.mlp.up_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-00001-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-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.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-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-00001-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00004-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-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "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.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-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-00004-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-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-00003-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-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-00001-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-00001-of-00004.safetensors",
-    "model.layers.22.input_layernorm.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-00001-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-00001-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-00003-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.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.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-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-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-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-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-00001-of-00004.safetensors",
     "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00001-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.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.bias": "model-00001-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-00001-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.25.mlp.up_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-00001-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "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-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-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-00001-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-00002-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00003-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-00002-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00001-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.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00003-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-00001-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-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-00004-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-00001-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-00003-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-00001-of-00004.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00003-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-00003-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-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-00002-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-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-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-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-00003-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-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-00001-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-00003-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-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-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.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.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.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-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-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.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-00001-of-00004.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-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-00004-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-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-00001-of-00004.safetensors",
     "model.layers.8.self_attn.v_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-00002-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.post_attention_layernorm.weight": "model-00004-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.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "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-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.norm.weight": "model-00003-of-00004.safetensors"
   }
 }