Add files using upload-large-folder tool

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -25,81 +25,81 @@
       "multi_modal_projector",
       "merger",
       "modality_projection",
-      "language_model.model.layers.4.self_attn",
-      "language_model.model.layers.2.self_attn",
+      "language_model.model.layers.1.mlp",
       "language_model.model.layers.13.mlp",
-      "language_model.model.layers.2.mlp",
-      "language_model.model.layers.11.mlp",
       "language_model.model.layers.3.self_attn",
-      "language_model.model.layers.12.mlp",
-      "language_model.model.layers.6.self_attn",
-      "language_model.model.layers.0.self_attn",
-      "language_model.model.layers.10.mlp",
-      "language_model.model.layers.5.self_attn",
-      "language_model.model.layers.9.mlp",
-      "language_model.model.layers.1.mlp",
-      "language_model.model.layers.0.mlp",
       "language_model.model.layers.4.mlp",
-      "language_model.model.layers.5.mlp",
-      "language_model.model.layers.8.mlp",
       "language_model.model.layers.7.self_attn",
-      "language_model.model.layers.3.mlp",
-      "language_model.model.layers.7.mlp",
+      "language_model.model.layers.0.mlp",
+      "language_model.model.layers.17.mlp",
+      "language_model.model.layers.18.self_attn",
+      "language_model.model.layers.5.mlp",
+      "language_model.model.layers.16.self_attn",
+      "language_model.model.layers.11.mlp",
+      "language_model.model.layers.19.self_attn",
       "language_model.model.layers.6.mlp",
+      "vision_tower.vision_model.encoder.layers.23.self_attn",
+      "language_model.model.layers.10.self_attn",
+      "language_model.model.layers.18.mlp",
+      "language_model.model.layers.8.mlp",
+      "language_model.model.layers.12.mlp",
       "vision_tower.vision_model.encoder.layers.26.self_attn",
-      "vision_tower.vision_model.encoder.layers.19.self_attn",
-      "vision_tower.vision_model.encoder.layers.25.mlp",
+      "language_model.model.layers.14.mlp",
+      "language_model.model.layers.7.mlp",
+      "language_model.model.layers.2.mlp",
+      "vision_tower.vision_model.encoder.layers.23.mlp",
+      "vision_tower.vision_model.encoder.layers.24.self_attn",
       "vision_tower.vision_model.encoder.layers.20.self_attn",
-      "vision_tower.vision_model.encoder.layers.18.self_attn",
-      "vision_tower.vision_model.encoder.layers.25.self_attn",
+      "vision_tower.vision_model.encoder.layers.21.self_attn",
+      "language_model.model.layers.3.mlp",
       "vision_tower.vision_model.encoder.layers.22.self_attn",
-      "vision_tower.vision_model.encoder.layers.15.mlp",
       "vision_tower.vision_model.encoder.layers.24.mlp",
+      "vision_tower.vision_model.encoder.layers.21.mlp",
+      "vision_tower.vision_model.encoder.layers.15.self_attn",
+      "vision_tower.vision_model.encoder.layers.16.self_attn",
+      "vision_tower.vision_model.encoder.layers.25.self_attn",
+      "vision_tower.vision_model.encoder.layers.18.mlp",
+      "vision_tower.vision_model.encoder.layers.15.mlp",
+      "vision_tower.vision_model.encoder.layers.18.self_attn",
       "vision_tower.vision_model.encoder.layers.17.self_attn",
-      "vision_tower.vision_model.encoder.layers.20.mlp",
+      "vision_tower.vision_model.encoder.layers.19.self_attn",
       "vision_tower.vision_model.encoder.layers.22.mlp",
+      "vision_tower.vision_model.encoder.layers.25.mlp",
       "vision_tower.vision_model.encoder.layers.17.mlp",
-      "vision_tower.vision_model.encoder.layers.16.mlp",
-      "vision_tower.vision_model.encoder.layers.23.mlp",
-      "vision_tower.vision_model.encoder.layers.16.self_attn",
-      "vision_tower.vision_model.encoder.layers.24.self_attn",
-      "vision_tower.vision_model.encoder.layers.23.self_attn",
+      "vision_tower.vision_model.encoder.layers.20.mlp",
       "vision_tower.vision_model.encoder.layers.19.mlp",
+      "vision_tower.vision_model.encoder.layers.13.mlp",
       "vision_tower.vision_model.encoder.layers.14.self_attn",
-      "vision_tower.vision_model.encoder.layers.12.mlp",
-      "vision_tower.vision_model.encoder.layers.15.self_attn",
-      "vision_tower.vision_model.encoder.layers.21.self_attn",
-      "vision_tower.vision_model.encoder.layers.21.mlp",
-      "vision_tower.vision_model.encoder.layers.10.mlp",
-      "vision_tower.vision_model.encoder.layers.13.self_attn",
+      "vision_tower.vision_model.encoder.layers.16.mlp",
       "vision_tower.vision_model.encoder.layers.14.mlp",
-      "vision_tower.vision_model.encoder.layers.13.mlp",
-      "vision_tower.vision_model.encoder.layers.18.mlp",
-      "vision_tower.vision_model.encoder.layers.11.mlp",
-      "vision_tower.vision_model.encoder.layers.9.mlp",
-      "vision_tower.vision_model.encoder.layers.8.mlp",
+      "vision_tower.vision_model.encoder.layers.13.self_attn",
+      "vision_tower.vision_model.encoder.layers.5.mlp",
       "vision_tower.vision_model.encoder.layers.10.self_attn",
-      "vision_tower.vision_model.encoder.layers.12.self_attn",
-      "vision_tower.vision_model.encoder.layers.6.mlp",
+      "vision_tower.vision_model.encoder.layers.8.mlp",
+      "vision_tower.vision_model.encoder.layers.9.mlp",
+      "vision_tower.vision_model.encoder.layers.11.mlp",
+      "vision_tower.vision_model.encoder.layers.6.self_attn",
+      "vision_tower.vision_model.encoder.layers.10.mlp",
+      "vision_tower.vision_model.encoder.layers.9.self_attn",
+      "vision_tower.vision_model.encoder.layers.11.self_attn",
       "vision_tower.vision_model.encoder.layers.8.self_attn",
+      "vision_tower.vision_model.encoder.layers.12.mlp",
       "vision_tower.vision_model.encoder.layers.7.mlp",
-      "vision_tower.vision_model.encoder.layers.11.self_attn",
-      "vision_tower.vision_model.encoder.layers.5.mlp",
-      "vision_tower.vision_model.encoder.layers.4.mlp",
-      "vision_tower.vision_model.encoder.layers.4.self_attn",
-      "vision_tower.vision_model.encoder.layers.7.self_attn",
-      "vision_tower.vision_model.encoder.layers.9.self_attn",
-      "vision_tower.vision_model.encoder.layers.6.self_attn",
-      "vision_tower.vision_model.encoder.layers.3.self_attn",
       "vision_tower.vision_model.encoder.layers.5.self_attn",
+      "vision_tower.vision_model.encoder.layers.12.self_attn",
+      "vision_tower.vision_model.encoder.layers.3.self_attn",
       "vision_tower.vision_model.encoder.layers.1.self_attn",
-      "vision_tower.vision_model.encoder.layers.1.mlp",
+      "vision_tower.vision_model.encoder.layers.6.mlp",
+      "vision_tower.vision_model.encoder.layers.7.self_attn",
+      "vision_tower.vision_model.encoder.layers.4.self_attn",
       "vision_tower.vision_model.encoder.layers.3.mlp",
-      "vision_tower.vision_model.encoder.layers.0.self_attn",
+      "vision_tower.vision_model.encoder.layers.4.mlp",
       "vision_tower.vision_model.encoder.layers.2.mlp",
-      "vision_tower.vision_model.encoder.layers.0.mlp",
+      "vision_tower.vision_model.encoder.layers.1.mlp",
       "vision_tower.vision_model.encoder.layers.2.self_attn",
-      "vision_tower.vision_model.encoder.layers.26.mlp"
+      "vision_tower.vision_model.encoder.layers.26.mlp",
+      "vision_tower.vision_model.encoder.layers.0.self_attn",
+      "vision_tower.vision_model.encoder.layers.0.mlp"
     ],
     "llm_int8_threshold": 6.0,
     "load_in_4bit": true,
@@ -137,7 +137,7 @@
     "vocab_size": 262208
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.0",
+  "transformers_version": "4.52.0.dev0",
   "unsloth_fixed": true,
   "vision_config": {
     "attention_dropout": 0.0,

generation_config.json

@@ -9,5 +9,5 @@
   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.51.0"
+  "transformers_version": "4.52.0.dev0"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1cdbe5e9e26335156628ea27119df51624116d1621e7fa8c497d83faeb75c5
-size 4909879825
+oid sha256:65c40514ec3214bd0c5fa5466cec219db978c16360382448a96bd6bf40b95dd6
+size 4960125164

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45468be8776aed37b4b129b0386c9de6a22d83ace45d37ba0f9eb598bc53cf0
-size 4974472887
+oid sha256:0396b9cc8d889d70cd1f15abc8827e22a14a1bfa3b156cd23339d4c106b8468e
+size 4970712399

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b13dfd800763fed1abb087b4df1c9ebf81274906559c1230fb6545e89602ca0c
-size 2690885809
+oid sha256:d3cd951c9b3acbfb4d5c19e2e6ff7bfd3cd285ad0e75832618ed3e98b6645ad6
+size 2836985438

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 12574916961
+    "total_size": 12767500929
   },
   "weight_map": {
     "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
@@ -13,10 +13,30 @@
     "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -52,37 +72,32 @@
     "language_model.model.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -184,23 +199,8 @@
     "language_model.model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -302,49 +302,14 @@
     "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -376,52 +341,17 @@
     "language_model.model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -446,30 +376,10 @@
     "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -479,10 +389,30 @@
     "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.20.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -627,28 +557,28 @@
     "language_model.model.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
     "language_model.model.layers.22.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
     "language_model.model.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
     "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
@@ -682,47 +612,47 @@
     "language_model.model.layers.24.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
     "language_model.model.layers.24.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
     "language_model.model.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
     "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
     "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.25.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
@@ -1456,19 +1386,39 @@
     "language_model.model.layers.39.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
     "language_model.model.layers.39.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
     "language_model.model.layers.39.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.40.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
@@ -1855,17 +1805,37 @@
     "language_model.model.layers.47.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
     "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
     "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -1875,10 +1845,30 @@
     "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -1927,8 +1917,23 @@
     "language_model.model.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",

tokenizer_config.json

@@ -51325,7 +51325,6 @@
   },
   "boi_token": "<start_of_image>",
   "bos_token": "<bos>",
-  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
   "eos_token": "<end_of_turn>",