scale_base_blend_dr @ step 650

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe4b872008be2cd3d564e69fa7811598e1307720c6ab0bce6c67148b375b8b8d
-size 4964924368
+oid sha256:9824e139960824e897614560a262acf7f30e91c445f4064001a9f07a4a262bea
+size 4971762376

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:549e66fb55f6d68e0e44cda8cbd56da6287d8fd86d34b57399b41141b041bf42
-size 1207002608
+oid sha256:f3bafa452dc69d20284a408171bf927a471f0ea20472adabb3f4ee0cbd6cf1fa
+size 1200164600

model.safetensors.index.json

@@ -4,55 +4,55 @@
     "total_size": 6171877376
   },
   "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
@@ -63,12 +63,12 @@
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
@@ -82,44 +82,44 @@
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
@@ -139,84 +139,84 @@
     "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
@@ -229,8 +229,8 @@
     "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -247,7 +247,7 @@
     "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -262,8 +262,8 @@
     "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
@@ -271,18 +271,18 @@
     "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -291,10 +291,10 @@
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -302,40 +302,40 @@
     "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
@@ -343,22 +343,22 @@
     "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
@@ -380,16 +380,16 @@
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
@@ -401,34 +401,34 @@
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
@@ -437,6 +437,6 @@
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors"
+    "model.norm.weight": "model-00001-of-00002.safetensors"
   }
 }