diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 12960084899
+    "total_size": 12189748992
   },
   "weight_map": {
     "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
@@ -13,30 +13,10 @@
     "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -72,8 +52,23 @@
     "language_model.model.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -138,23 +133,8 @@
     "language_model.model.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -208,80 +188,105 @@
     "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -335,10 +340,30 @@
     "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -363,10 +388,30 @@
     "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -430,17 +475,52 @@
     "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.21.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -489,294 +569,294 @@
     "language_model.model.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
     "language_model.model.layers.21.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
     "language_model.model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.28.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
@@ -799,32 +879,32 @@
     "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.29.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
@@ -882,30 +962,10 @@
     "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.30.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
@@ -1386,39 +1446,19 @@
     "language_model.model.layers.39.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
     "language_model.model.layers.39.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
     "language_model.model.layers.39.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.40.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
@@ -1805,37 +1845,17 @@
     "language_model.model.layers.47.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
     "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -1845,30 +1865,10 @@
     "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -1878,30 +1878,10 @@
     "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",