Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if message['role'] == 'user' %}{{'<|user|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
+' + message['content'] + '<|end|>
+'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
+' }}{% else %}{{ eos_token }}{% endif %}

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "unsloth/Phi-3-medium-4k-instruct",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -26,7 +25,12 @@
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
     "llm_int8_threshold": 6.0,
     "load_in_4bit": true,
     "load_in_8bit": false,
@@ -37,7 +41,8 @@
   "sliding_window": 2048,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.52.4",
+  "unsloth_fixed": true,
   "unsloth_version": "2024.9",
   "use_cache": true,
   "vocab_size": 32064

generation_config.json

@@ -8,5 +8,5 @@
   ],
   "max_length": 4096,
   "pad_token_id": 32009,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.52.4"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abd55e6507f78a871fd0aef10de5ee1bf33dfaa1fba2fd87742e7c153ce2871
-size 3973540632
+oid sha256:48ea427b2e4813a780a8f2d48cce981b63a05e6a9e23f2596b044fa59c5c9cad
+size 4981224634

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948a89aa8aa57bb066f4af8910ea2d6e34810c70120087b20e2b7b154e002885
-size 3716586791
+oid sha256:4a99aab3d6116f716f66760186c1ad07d07da157126654477d64bc2cc81e753b
+size 2708902797

model.safetensors.index.json

@@ -577,13 +577,13 @@
     "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-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.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.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",
@@ -596,7 +596,7 @@
     "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-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "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",
     "model.layers.20.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -621,226 +621,226 @@
     "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-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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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-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",
@@ -848,12 +848,12 @@
     "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.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-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",
@@ -861,30 +861,30 @@
     "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.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.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.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.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.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.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-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",

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|placeholder6|>",
+  "pad_token": {
+    "content": "<|placeholder6|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -117,9 +117,9 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 4096,
   "pad_token": "<|placeholder6|>",
@@ -127,5 +127,6 @@
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}
+  "use_default_system_prompt": false,
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}"
+}