diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,22 +1,57 @@
 {
   "metadata": {
-    "total_size": 13849798100
+    "total_size": 10247200062
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -24,485 +59,520 @@
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
@@ -531,100 +601,100 @@
     "model.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -700,6 +770,11 @@
     "model.layers.23.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -810,8 +885,23 @@
     "model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
@@ -983,16 +1073,51 @@
     "model.layers.29.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -1369,26 +1494,26 @@
     "model.layers.37.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
     "model.layers.37.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
     "model.layers.37.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.38.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
     "model.layers.38.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
     "model.layers.38.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
     "model.layers.38.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
     "model.layers.38.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.38.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
     "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.38.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -1416,395 +1541,495 @@
     "model.layers.38.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
     "model.layers.38.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
     "model.layers.38.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.39.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.40.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.41.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.41.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.42.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.42.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.43.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.43.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.44.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.46.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "model.layers.47.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
@@ -1833,11 +2058,26 @@
     "model.layers.5.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
@@ -1865,147 +2105,147 @@
     "model.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors"
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00002-of-00003.safetensors"
   }
 }