diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,10 +1,9 @@
 {
   "metadata": {
-    "total_size": 11277690438
+    "total_size": 12619729990
   },
   "weight_map": {
     "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
-    "language_model.lm_head.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
@@ -38,73 +37,73 @@
     "language_model.model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.k_norm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.q_norm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn_attn_gate": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn_mlp_gate": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn_attn_gate": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.cross_attn_mlp_gate": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -458,74 +457,74 @@
     "language_model.model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.cross_attn_attn_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.33.cross_attn_mlp_gate": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.36.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
@@ -681,7 +680,6 @@
     "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
     "multi_modal_projector.bias": "model-00003-of-00003.safetensors",
     "multi_modal_projector.weight": "model-00003-of-00003.safetensors",
-    "multi_modal_projector.weight_scale": "model-00003-of-00003.safetensors",
     "vision_model.class_embedding": "model-00001-of-00003.safetensors",
     "vision_model.gated_positional_embedding.embedding": "model-00001-of-00003.safetensors",
     "vision_model.gated_positional_embedding.gate": "model-00001-of-00003.safetensors",
@@ -692,160 +690,112 @@
     "vision_model.global_transformer.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.0.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.0.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.gate_attn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.gate_ffn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.1.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.1.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.gate_attn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.gate_ffn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.2.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.2.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.gate_attn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.gate_ffn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.3.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.3.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.gate_attn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.gate_ffn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.4.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.4.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.gate_attn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.gate_ffn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.5.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.5.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.gate_attn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.gate_ffn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.6.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.6.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.gate_attn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.gate_ffn": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.7.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.7.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.global_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.layernorm_post.bias": "model-00001-of-00003.safetensors",
     "vision_model.layernorm_post.weight": "model-00001-of-00003.safetensors",
     "vision_model.layernorm_pre.bias": "model-00001-of-00003.safetensors",
@@ -859,577 +809,385 @@
     "vision_model.transformer.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.0.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.0.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.1.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.1.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.10.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.10.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.11.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.11.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.12.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.12.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.13.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.13.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.14.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.14.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.15.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.15.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.16.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.16.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.17.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.17.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.18.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.18.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.19.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.19.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.2.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.2.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.20.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.20.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.21.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.21.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.22.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.22.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.23.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.23.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.24.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.24.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.25.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.25.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.26.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.26.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.26.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.26.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.27.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.27.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.27.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.27.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.28.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.28.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.28.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.28.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.29.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.29.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.29.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.29.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.3.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.3.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.30.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.30.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.30.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.30.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.31.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.31.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.31.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.31.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.31.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.4.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.4.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.5.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.5.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.6.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.6.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.7.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.7.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.8.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.8.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.9.mlp.fc1.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.9.mlp.fc2.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "vision_model.transformer.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors"
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
   }
 }