diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 7357999463
+    "total_size": 7179459873
   },
   "weight_map": {
     "language_model.lm_head.weight": "model-00002-of-00002.safetensors",
@@ -37,22 +37,18 @@
     "language_model.model.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.1.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -85,22 +81,18 @@
     "language_model.model.layers.1.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.1.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.10.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -133,22 +125,18 @@
     "language_model.model.layers.10.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.10.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.11.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -181,22 +169,18 @@
     "language_model.model.layers.11.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.11.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.12.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -229,22 +213,18 @@
     "language_model.model.layers.12.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.12.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.cross_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.cross_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.cross_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -259,22 +239,18 @@
     "language_model.model.layers.13.cross_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.cross_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.cross_attn_attn_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.cross_attn_mlp_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -329,22 +305,18 @@
     "language_model.model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.14.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.15.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -377,22 +349,18 @@
     "language_model.model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.15.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.16.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -425,22 +393,18 @@
     "language_model.model.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.16.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.17.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -473,22 +437,18 @@
     "language_model.model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.17.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.18.cross_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.18.cross_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.18.cross_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -503,22 +463,18 @@
     "language_model.model.layers.18.cross_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.18.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.18.cross_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.18.cross_attn_attn_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.18.cross_attn_mlp_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -573,22 +529,18 @@
     "language_model.model.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.19.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -621,22 +573,18 @@
     "language_model.model.layers.2.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.20.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -669,22 +617,18 @@
     "language_model.model.layers.20.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.20.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.21.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -717,22 +661,18 @@
     "language_model.model.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.21.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.22.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -765,22 +705,18 @@
     "language_model.model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.22.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.23.cross_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.23.cross_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.23.cross_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -795,22 +731,18 @@
     "language_model.model.layers.23.cross_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.23.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.23.cross_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.23.cross_attn_attn_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.23.cross_attn_mlp_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -865,22 +797,18 @@
     "language_model.model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.24.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.25.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -913,22 +841,18 @@
     "language_model.model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.25.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.26.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -961,22 +885,18 @@
     "language_model.model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.26.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.27.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1009,22 +929,18 @@
     "language_model.model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.27.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.cross_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.cross_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.cross_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1039,92 +955,84 @@
     "language_model.model.layers.28.cross_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.cross_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.cross_attn_attn_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.cross_attn_mlp_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.28.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.cross_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.cross_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.cross_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1139,22 +1047,18 @@
     "language_model.model.layers.3.cross_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.cross_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.cross_attn_attn_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.cross_attn_mlp_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -1197,34 +1101,30 @@
     "language_model.model.layers.30.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.30.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.31.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -1257,22 +1157,18 @@
     "language_model.model.layers.31.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.31.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.32.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -1305,22 +1201,18 @@
     "language_model.model.layers.32.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.32.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.32.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.33.cross_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -1335,22 +1227,18 @@
     "language_model.model.layers.33.cross_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.33.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.33.cross_attn_attn_gate": "model-00002-of-00002.safetensors",
     "language_model.model.layers.33.cross_attn_mlp_gate": "model-00002-of-00002.safetensors",
     "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -1405,22 +1293,18 @@
     "language_model.model.layers.34.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.34.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.34.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.35.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -1453,22 +1337,18 @@
     "language_model.model.layers.35.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.35.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.35.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.36.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -1501,22 +1381,18 @@
     "language_model.model.layers.36.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.36.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.36.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.37.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -1549,22 +1425,18 @@
     "language_model.model.layers.37.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.37.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.37.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.38.cross_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.38.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.38.cross_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -1579,22 +1451,18 @@
     "language_model.model.layers.38.cross_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.38.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.38.cross_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.38.cross_attn_attn_gate": "model-00002-of-00002.safetensors",
     "language_model.model.layers.38.cross_attn_mlp_gate": "model-00002-of-00002.safetensors",
     "language_model.model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -1649,22 +1517,18 @@
     "language_model.model.layers.39.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.39.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "language_model.model.layers.39.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.base_layer.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.base_layer.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.4.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1697,22 +1561,18 @@
     "language_model.model.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.5.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1745,22 +1605,18 @@
     "language_model.model.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.5.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.6.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1793,22 +1649,18 @@
     "language_model.model.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.6.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.7.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1841,22 +1693,18 @@
     "language_model.model.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.7.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.8.cross_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.8.cross_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.8.cross_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1871,22 +1719,18 @@
     "language_model.model.layers.8.cross_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.8.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.8.cross_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.8.cross_attn_attn_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.8.cross_attn_mlp_gate": "model-00001-of-00002.safetensors",
     "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -1941,22 +1785,18 @@
     "language_model.model.layers.9.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.9.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
     "multi_modal_projector.bias": "model-00002-of-00002.safetensors",
     "multi_modal_projector.weight": "model-00002-of-00002.safetensors",
@@ -2001,22 +1841,18 @@
     "vision_model.global_transformer.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.1.gate_attn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.1.gate_ffn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
@@ -2049,22 +1885,18 @@
     "vision_model.global_transformer.layers.1.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.1.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.2.gate_attn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.2.gate_ffn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
@@ -2097,22 +1929,18 @@
     "vision_model.global_transformer.layers.2.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.2.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.3.gate_attn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.3.gate_ffn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
@@ -2145,22 +1973,18 @@
     "vision_model.global_transformer.layers.3.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.3.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.4.gate_attn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.4.gate_ffn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
@@ -2193,22 +2017,18 @@
     "vision_model.global_transformer.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.5.gate_attn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.5.gate_ffn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
@@ -2241,22 +2061,18 @@
     "vision_model.global_transformer.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.5.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.6.gate_attn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.6.gate_ffn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
@@ -2289,22 +2105,18 @@
     "vision_model.global_transformer.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.6.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.7.gate_attn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.7.gate_ffn": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
@@ -2337,22 +2149,18 @@
     "vision_model.global_transformer.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.7.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.global_transformer.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.global_transformer.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.layernorm_post.bias": "model-00001-of-00002.safetensors",
     "vision_model.layernorm_post.weight": "model-00001-of-00002.safetensors",
     "vision_model.layernorm_pre.bias": "model-00001-of-00002.safetensors",
@@ -2392,22 +2200,18 @@
     "vision_model.transformer.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2438,22 +2242,18 @@
     "vision_model.transformer.layers.1.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.1.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2484,22 +2284,18 @@
     "vision_model.transformer.layers.10.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.10.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2530,22 +2326,18 @@
     "vision_model.transformer.layers.11.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.11.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2576,22 +2368,18 @@
     "vision_model.transformer.layers.12.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.12.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2622,22 +2410,18 @@
     "vision_model.transformer.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.13.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2668,22 +2452,18 @@
     "vision_model.transformer.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.14.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2714,22 +2494,18 @@
     "vision_model.transformer.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.15.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2760,22 +2536,18 @@
     "vision_model.transformer.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.16.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2806,22 +2578,18 @@
     "vision_model.transformer.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.17.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2852,22 +2620,18 @@
     "vision_model.transformer.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.18.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2898,22 +2662,18 @@
     "vision_model.transformer.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.19.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2944,22 +2704,18 @@
     "vision_model.transformer.layers.2.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.2.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -2990,22 +2746,18 @@
     "vision_model.transformer.layers.20.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.20.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3036,22 +2788,18 @@
     "vision_model.transformer.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.21.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3082,22 +2830,18 @@
     "vision_model.transformer.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.22.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3128,22 +2872,18 @@
     "vision_model.transformer.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.23.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3174,22 +2914,18 @@
     "vision_model.transformer.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.24.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3220,22 +2956,18 @@
     "vision_model.transformer.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.25.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3266,22 +2998,18 @@
     "vision_model.transformer.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.26.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3312,22 +3040,18 @@
     "vision_model.transformer.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.27.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3358,22 +3082,18 @@
     "vision_model.transformer.layers.28.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.28.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.28.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.28.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3404,22 +3124,18 @@
     "vision_model.transformer.layers.29.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.29.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.29.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.29.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3450,22 +3166,18 @@
     "vision_model.transformer.layers.3.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.3.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.30.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.30.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3496,22 +3208,18 @@
     "vision_model.transformer.layers.30.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.30.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.30.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.30.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.31.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.31.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3542,22 +3250,18 @@
     "vision_model.transformer.layers.31.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.31.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3588,22 +3292,18 @@
     "vision_model.transformer.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3634,22 +3334,18 @@
     "vision_model.transformer.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.5.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3680,22 +3376,18 @@
     "vision_model.transformer.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.6.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3726,22 +3418,18 @@
     "vision_model.transformer.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.7.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3772,22 +3460,18 @@
     "vision_model.transformer.layers.8.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.8.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
@@ -3818,21 +3502,17 @@
     "vision_model.transformer.layers.9.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.9.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "vision_model.transformer.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.base_layer.weight.absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.base_layer.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.base_layer.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.base_layer.weight.quant_map": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.base_layer.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
-    "vision_model.transformer.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors"
+    "vision_model.transformer.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors"
   }
 }