Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,22 @@
+---
+license: apache-2.0
+base_model:
+- Qwen/Qwen3-VL-2B-Instruct
+tags:
+- abliterated
+- uncensored
+- mlx
+---
+
+# EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-4bit-g32-mixed_4_8-mlx
+This model was converted to MLX format from [`huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated`]() using mlx-vlm version **0.3.4**.
+Refer to the [original model card](https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-4bit-g32-mixed_4_8-mlx --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+```

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

chat_template.json

@@ -0,0 +1,4 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}
+  

config.json

@@ -0,0 +1,1822 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "Qwen3VLForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dtype": null,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "image_token_id": 151655,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "qwen3_vl",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.embed_tokens": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        }
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.embed_tokens": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "language_model.model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        }
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "text_config": {
+        "vocab_size": 151936,
+        "max_position_embeddings": 262144,
+        "hidden_size": 2048,
+        "intermediate_size": 6144,
+        "num_hidden_layers": 28,
+        "num_attention_heads": 16,
+        "num_key_value_heads": 8,
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-06,
+        "use_cache": true,
+        "rope_theta": 5000000,
+        "rope_scaling": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                24,
+                20,
+                20
+            ],
+            "rope_type": "default"
+        },
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "dtype": "bfloat16",
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "task_specific_params": null,
+        "problem_type": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": 151643,
+        "pad_token_id": null,
+        "eos_token_id": 151645,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "_name_or_path": "",
+        "model_type": "qwen3_vl_text",
+        "tf_legacy_loss": false,
+        "use_bfloat16": false,
+        "output_attentions": false
+    },
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.57.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "video_token_id": 151656,
+    "vision_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "dtype": null,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "task_specific_params": null,
+        "problem_type": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "_name_or_path": "",
+        "model_type": "qwen3_vl",
+        "tf_legacy_loss": false,
+        "use_bfloat16": false,
+        "depth": 24,
+        "hidden_size": 1024,
+        "hidden_act": "gelu_pytorch_tanh",
+        "intermediate_size": 4096,
+        "num_heads": 16,
+        "in_channels": 3,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2,
+        "out_hidden_size": 2048,
+        "num_position_embeddings": 2304,
+        "initializer_range": 0.02,
+        "deepstack_visual_indexes": [
+            5,
+            11,
+            17
+        ],
+        "output_attentions": false
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "top_p": 0.8,
+    "top_k": 20,
+    "temperature": 0.7,
+    "repetition_penalty": 1.0,
+    "transformers_version": "4.56.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165fc31d188f90b7ecbfc15270ba6ad24742cd23fe08d5ddec5fa3d4c5f404ff
+size 2040383945

model.safetensors.index.json

@@ -0,0 +1,1026 @@
+{
+    "metadata": {
+        "total_size": 2040258560
+    },
+    "weight_map": {
+        "language_model.model.embed_tokens.biases": "model.safetensors",
+        "language_model.model.embed_tokens.scales": "model.safetensors",
+        "language_model.model.embed_tokens.weight": "model.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.24.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.25.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.26.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.norm.weight": "model.safetensors",
+        "vision_tower.blocks.0.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.0.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.0.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.0.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.0.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.0.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.0.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.0.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.0.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.0.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.0.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.0.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.1.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.1.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.1.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.1.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.1.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.1.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.1.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.1.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.1.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.1.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.1.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.1.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.10.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.10.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.10.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.10.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.10.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.10.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.10.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.10.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.10.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.10.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.10.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.10.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.11.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.11.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.11.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.11.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.11.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.11.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.11.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.11.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.11.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.11.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.11.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.11.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.12.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.12.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.12.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.12.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.12.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.12.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.12.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.12.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.12.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.12.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.12.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.12.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.13.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.13.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.13.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.13.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.13.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.13.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.13.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.13.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.13.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.13.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.13.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.13.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.14.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.14.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.14.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.14.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.14.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.14.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.14.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.14.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.14.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.14.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.14.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.14.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.15.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.15.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.15.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.15.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.15.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.15.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.15.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.15.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.15.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.15.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.15.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.15.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.16.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.16.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.16.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.16.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.16.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.16.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.16.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.16.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.16.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.16.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.16.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.16.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.17.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.17.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.17.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.17.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.17.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.17.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.17.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.17.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.17.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.17.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.17.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.17.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.18.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.18.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.18.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.18.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.18.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.18.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.18.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.18.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.18.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.18.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.18.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.18.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.19.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.19.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.19.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.19.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.19.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.19.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.19.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.19.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.19.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.19.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.19.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.19.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.2.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.2.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.2.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.2.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.2.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.2.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.2.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.2.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.2.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.2.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.2.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.2.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.20.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.20.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.20.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.20.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.20.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.20.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.20.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.20.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.20.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.20.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.20.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.20.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.21.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.21.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.21.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.21.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.21.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.21.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.21.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.21.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.21.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.21.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.21.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.21.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.22.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.22.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.22.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.22.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.22.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.22.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.22.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.22.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.22.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.22.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.22.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.22.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.23.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.23.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.23.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.23.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.23.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.23.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.23.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.23.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.23.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.23.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.23.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.23.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.3.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.3.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.3.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.3.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.3.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.3.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.3.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.3.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.3.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.3.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.3.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.3.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.4.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.4.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.4.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.4.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.4.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.4.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.4.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.4.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.4.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.4.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.4.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.4.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.5.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.5.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.5.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.5.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.5.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.5.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.5.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.5.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.5.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.5.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.5.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.5.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.6.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.6.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.6.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.6.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.6.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.6.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.6.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.6.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.6.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.6.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.6.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.6.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.7.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.7.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.7.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.7.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.7.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.7.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.7.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.7.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.7.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.7.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.7.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.7.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.8.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.8.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.8.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.8.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.8.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.8.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.8.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.8.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.8.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.8.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.8.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.8.norm2.weight": "model.safetensors",
+        "vision_tower.blocks.9.attn.proj.bias": "model.safetensors",
+        "vision_tower.blocks.9.attn.proj.weight": "model.safetensors",
+        "vision_tower.blocks.9.attn.qkv.bias": "model.safetensors",
+        "vision_tower.blocks.9.attn.qkv.weight": "model.safetensors",
+        "vision_tower.blocks.9.mlp.linear_fc1.bias": "model.safetensors",
+        "vision_tower.blocks.9.mlp.linear_fc1.weight": "model.safetensors",
+        "vision_tower.blocks.9.mlp.linear_fc2.bias": "model.safetensors",
+        "vision_tower.blocks.9.mlp.linear_fc2.weight": "model.safetensors",
+        "vision_tower.blocks.9.norm1.bias": "model.safetensors",
+        "vision_tower.blocks.9.norm1.weight": "model.safetensors",
+        "vision_tower.blocks.9.norm2.bias": "model.safetensors",
+        "vision_tower.blocks.9.norm2.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.0.linear_fc1.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.0.linear_fc1.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.0.linear_fc2.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.0.linear_fc2.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.0.norm.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.0.norm.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.1.linear_fc1.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.1.linear_fc1.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.1.linear_fc2.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.1.linear_fc2.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.1.norm.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.1.norm.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.2.linear_fc1.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.2.linear_fc1.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.2.linear_fc2.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.2.linear_fc2.weight": "model.safetensors",
+        "vision_tower.deepstack_merger_list.2.norm.bias": "model.safetensors",
+        "vision_tower.deepstack_merger_list.2.norm.weight": "model.safetensors",
+        "vision_tower.merger.linear_fc1.bias": "model.safetensors",
+        "vision_tower.merger.linear_fc1.weight": "model.safetensors",
+        "vision_tower.merger.linear_fc2.bias": "model.safetensors",
+        "vision_tower.merger.linear_fc2.weight": "model.safetensors",
+        "vision_tower.merger.norm.bias": "model.safetensors",
+        "vision_tower.merger.norm.weight": "model.safetensors",
+        "vision_tower.patch_embed.proj.bias": "model.safetensors",
+        "vision_tower.patch_embed.proj.weight": "model.safetensors",
+        "vision_tower.pos_embed.weight": "model.safetensors"
+    }
+}

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}