Upload folder using huggingface_hub

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47a09ebcc60b370c78439947510fd0ea4debac3ca69d6cb6039c77ce2170909
-size 4382185960
+oid sha256:a0a60e4cfdfb220cc9f5751b3c4376e5549e2684be7a45b3536bf807feaa4ab9
+size 4925341320

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a5ab2d35d204a9ea75dbf98c0de9606e9ccf5d4525cc47b58fc7993b0fcc9c
-size 4903421192
+oid sha256:23a4c3cb803d040481abd10db4be7cdf45bf062347887e5fc491987320ad1f06
+size 4976780040

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb379e11c7aac146f746706eba46998462d235ff07d3c352fba66c262d75bbe
-size 4877648528
+oid sha256:6dd96a5d4ee87c08b411742f7381daf0bea32ad5a33e94fedc78797f8d3e10f3
+size 4866704792

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733640ed48280f2220122f4a697ead30a7e793a1db69a6de61e2408a75ae48d9
-size 1068016216
+oid sha256:c8fb93f35f90d2db51961b144c372193596dc6589265dd7c33bb923cc0f7c818
+size 462445712

model.safetensors.index.json

@@ -3,342 +3,342 @@
     "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-00001-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00002-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.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00002-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-00001-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-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00004-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-00002-of-00004.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.1.post_attention_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-00003-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-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00003-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-00002-of-00004.safetensors",
-    "model.layers.1.self_attn.v_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-00002-of-00004.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.up_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-00002-of-00004.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.10.self_attn.o_proj.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-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-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-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-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-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-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-00003-of-00004.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-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-00001-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00002-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-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-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-00002-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-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.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-00002-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-00003-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-00001-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-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.12.self_attn.k_proj.weight": "model-00001-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-00002-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.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
-    "model.layers.13.self_attn.q_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-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-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.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-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.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-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-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-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-00003-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-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-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.bias": "model-00003-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-00004-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-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-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-00003-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00001-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-00001-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-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-00003-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-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-00001-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-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "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-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-00002-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-00001-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.v_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-00002-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.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.post_attention_layernorm.weight": "model-00004-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-00003-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-00001-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-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-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.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00002-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-00001-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-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-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-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-00003-of-00004.safetensors",
-    "model.layers.2.mlp.down_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-00002-of-00004.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.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-00003-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-00002-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00001-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-00002-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-00003-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00001-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-00002-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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-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-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "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.21.post_attention_layernorm.weight": "model-00002-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-00003-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-00001-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-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-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-00002-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-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-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-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-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-00002-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.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "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-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00003-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-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00001-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.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-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-00003-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-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-00002-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-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-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-00001-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.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-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-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-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-00001-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "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.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-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-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.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-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-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-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-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-00001-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-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-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-00002-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-00001-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-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.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-00002-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-00003-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00004-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-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-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.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-00003-of-00004.safetensors",
-    "model.layers.4.mlp.down_proj.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-00003-of-00004.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-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-00004-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-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.v_proj.bias": "model-00004-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-00002-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.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "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-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-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-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00004-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-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-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-00001-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.bias": "model-00002-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-00004-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-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-00001-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.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00004-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-00002-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-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-00003-of-00004.safetensors",
     "model.layers.7.self_attn.v_proj.bias": "model-00003-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.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00003-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-00004-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-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-00001-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-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-00003-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-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-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-00004-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-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-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-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-00002-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.norm.weight": "model-00002-of-00004.safetensors"