Upload MllamaForConditionalGeneration

config.json

@@ -21,6 +21,7 @@
     "quant_method": "bitsandbytes"
   },
   "text_config": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "",
     "add_cross_attention": false,
     "architectures": null,
@@ -114,8 +115,10 @@
     "vocab_size": 128256
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.0",
+  "transformers_version": "4.46.3",
+  "unsloth_fixed": true,
   "vision_config": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "",
     "add_cross_attention": false,
     "architectures": null,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 128000,
   "eos_token_id": 128001,
   "pad_token_id": 128004,
-  "transformers_version": "4.45.0"
+  "transformers_version": "4.46.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e69f8fcdfd5863e6bfa5b57101d06d00ff078b11e372ca71cbb4bde23882a42
-size 4984953659
+oid sha256:449b885c3695adb34f8184e1b499b3f0244de9eceaa67b3055cded34683557f8
+size 6058466370

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48975aae8e6a2efcb65673e54d170db7958a59aedcecb4b03bb6b0e5e33342f8
-size 2140423619
+oid sha256:49625c07f1a5518f9bfd693bc8256a579a91ed6c4617abf2075f44074fb9abf3
+size 1066911340

model.safetensors.index.json

@@ -1081,26 +1081,26 @@
     "language_model.model.layers.3.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1125,410 +1125,410 @@
     "language_model.model.layers.30.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.30.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn_attn_gate": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.cross_attn_mlp_gate": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn_attn_gate": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.cross_attn_mlp_gate": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn_attn_gate": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.cross_attn_mlp_gate": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn_attn_gate": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.cross_attn_mlp_gate": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.4.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1797,7 +1797,7 @@
     "language_model.model.layers.9.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.9.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "language_model.model.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.norm.weight": "model-00001-of-00002.safetensors",
     "multi_modal_projector.bias": "model-00002-of-00002.safetensors",
     "multi_modal_projector.weight": "model-00002-of-00002.safetensors",
     "multi_modal_projector.weight.absmax": "model-00002-of-00002.safetensors",