Upload Qwen2_5_VLForConditionalGeneration

config.json

@@ -44,7 +44,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "use_cache": true,
   "use_sliding_window": false,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8ef7bec75e337ef6eab96b84e740ba2f261d75eb8ea89e08b5845531232d7c9
-size 4809612533
+oid sha256:8027ed4558648a8104ebd39e32d3a5453de8b3e2b2318311ae9f9fcb5588ffb3
+size 4992162636

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c859795ad3a627a9b95bcb762e059d5b768a4a36fdd4affeff269d93fdecc67
-size 1089994880
+oid sha256:a36f454c4f66110e46750ee133e71b32db2a4f226ace3802f55ff66483092915
+size 3092067506

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5899313093
+    "total_size": 8083929022
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -616,26 +616,26 @@
     "model.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -663,335 +663,335 @@
     "model.layers.20.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1321,7 +1321,7 @@
     "model.layers.9.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
     "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
     "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
     "visual.blocks.0.attn.proj.weight.absmax": "model-00001-of-00002.safetensors",