Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1832/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-VL-4B-Thinking
+library_name: transformers
+model_name: test-full-pipeline
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for test-full-pipeline
+
+This model is a fine-tuned version of [Qwen/Qwen3-VL-4B-Thinking](https://huggingface.co/Qwen/Qwen3-VL-4B-Thinking).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mjf-su-stanford-university/wds-single-shard/runs/ssph0syr) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.26.1
+- Transformers: 4.57.1
+- Pytorch: 2.9.0
+- Datasets: 4.4.1
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

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 +1,110 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- else %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                <|vision_start|><|image_pad|><|vision_end|>
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                <|vision_start|><|video_pad|><|vision_end|>
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{%- endmacro %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- render_content(messages[0].content, false) + '\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' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false) %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, True) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and 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' }}
+        {{- content }}
+        {{- '\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 %}

checkpoint-1000/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
+}

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,110 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- else %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                <|vision_start|><|image_pad|><|vision_end|>
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                <|vision_start|><|video_pad|><|vision_end|>
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{%- endmacro %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- render_content(messages[0].content, false) + '\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' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false) %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, True) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and 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' }}
+        {{- content }}
+        {{- '\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 %}

checkpoint-1000/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

checkpoint-1000/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96633ec6bb2d7d8df8ec117b64fb813015310f60e45c53400b4b3d2f98c9cc23
+size 4990497880

checkpoint-1000/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b9ee9c9453f7c8825ada1058d41827da9ad1a3ca4ce8ed07cf76902e9d5cd8
+size 3885221448

checkpoint-1000/model.safetensors.index.json

@@ -0,0 +1,721 @@
+{
+  "metadata": {
+    "total_parameters": 4437815808,
+    "total_size": 8875631616
+  },
+  "weight_map": {
+    "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+  }
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9d61693293fae033bd67335ebaadfe1a38a8265eb480adb4c8c24e69361800
+size 17751894342

checkpoint-1000/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
+}

checkpoint-1000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478b41e9f26d338fd8f896e08cad1adab7c423b61f1b45754113bc78d256a3f9
+size 16389

checkpoint-1000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce29a8767a7d907dd24987aa2c3e654d4317f3042fbc13b5b72cadb46d43311a
+size 16389

checkpoint-1000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a48db011646b4e9a867bf12f4a233cad5dfbfe309686f8996c250196d3783a
+size 16389

checkpoint-1000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9562ee822472a4f01dcd6349ab3d1ef42a48915fe3b92e843a0c37db53c8421
+size 16389

checkpoint-1000/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d2767d83c3bf27f12db022b0632e2c4f8c164274ba75e380cf18f9d5f21819
+size 16389

checkpoint-1000/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76816358d4e5db8149d60d55234db658d67a13c0c1ce05d7404cf7125a676a5c
+size 16389

checkpoint-1000/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1562e7520c977d178183d641f70abcf3f57da2489938756cfbebf9b6e6c1a9fd
+size 16389

checkpoint-1000/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b6cabaed045c5398cd1b732f7ec48bd363f3b43cd24e0e70e641a42bd00c28
+size 16389

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5983aafce3d2df0573a37c5a96a7adc1ea3ffa7297a9fbfbb9293795dc63b1f
+size 1465

checkpoint-1000/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
+  }
+}

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b55fa0c3aba0c91ce09ea79ae4e62da24e2a1a630f96c4bae34aba25e234a
+size 11422822

checkpoint-1000/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
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1034 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5458515283842795,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8506594449281693,
+      "epoch": 0.0054585152838427945,
+      "grad_norm": 6.625,
+      "learning_rate": 1.6363636363636365e-06,
+      "loss": 0.7328,
+      "mean_token_accuracy": 0.8114667266607285,
+      "num_tokens": 7873074.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.8578470677137375,
+      "epoch": 0.010917030567685589,
+      "grad_norm": 3.234375,
+      "learning_rate": 3.454545454545455e-06,
+      "loss": 0.6724,
+      "mean_token_accuracy": 0.8153360992670059,
+      "num_tokens": 15735890.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.868700721859932,
+      "epoch": 0.016375545851528384,
+      "grad_norm": 0.94140625,
+      "learning_rate": 5.272727272727273e-06,
+      "loss": 0.5629,
+      "mean_token_accuracy": 0.8309339731931686,
+      "num_tokens": 23601330.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8585465878248215,
+      "epoch": 0.021834061135371178,
+      "grad_norm": 0.58984375,
+      "learning_rate": 7.0909090909090916e-06,
+      "loss": 0.5071,
+      "mean_token_accuracy": 0.8447592586278916,
+      "num_tokens": 31458560.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8470574885606765,
+      "epoch": 0.027292576419213975,
+      "grad_norm": 0.5078125,
+      "learning_rate": 8.90909090909091e-06,
+      "loss": 0.4817,
+      "mean_token_accuracy": 0.8515126377344131,
+      "num_tokens": 39318330.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8366546362638474,
+      "epoch": 0.03275109170305677,
+      "grad_norm": 0.412109375,
+      "learning_rate": 9.999874978970385e-06,
+      "loss": 0.4536,
+      "mean_token_accuracy": 0.8550278633832932,
+      "num_tokens": 47187690.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.8242797136306763,
+      "epoch": 0.03820960698689956,
+      "grad_norm": 0.5,
+      "learning_rate": 9.998468564187713e-06,
+      "loss": 0.4452,
+      "mean_token_accuracy": 0.8588810175657272,
+      "num_tokens": 55058356.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8176750153303146,
+      "epoch": 0.043668122270742356,
+      "grad_norm": 0.447265625,
+      "learning_rate": 9.995499899369634e-06,
+      "loss": 0.4375,
+      "mean_token_accuracy": 0.860920637845993,
+      "num_tokens": 62923390.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.8128144711256027,
+      "epoch": 0.04912663755458515,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.990969912359675e-06,
+      "loss": 0.4483,
+      "mean_token_accuracy": 0.8596585601568222,
+      "num_tokens": 70785326.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.8117900550365448,
+      "epoch": 0.05458515283842795,
+      "grad_norm": 0.486328125,
+      "learning_rate": 9.984880018985966e-06,
+      "loss": 0.4368,
+      "mean_token_accuracy": 0.8614727318286896,
+      "num_tokens": 78646604.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.8099668920040131,
+      "epoch": 0.060043668122270744,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.977232122618704e-06,
+      "loss": 0.4429,
+      "mean_token_accuracy": 0.8630078643560409,
+      "num_tokens": 86509996.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.8032392680644989,
+      "epoch": 0.06550218340611354,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.968028613575292e-06,
+      "loss": 0.4483,
+      "mean_token_accuracy": 0.8638610720634461,
+      "num_tokens": 94374220.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.7966970652341843,
+      "epoch": 0.07096069868995633,
+      "grad_norm": 0.546875,
+      "learning_rate": 9.957272368373235e-06,
+      "loss": 0.4306,
+      "mean_token_accuracy": 0.8641012936830521,
+      "num_tokens": 102245070.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.7891126424074173,
+      "epoch": 0.07641921397379912,
+      "grad_norm": 0.65234375,
+      "learning_rate": 9.944966748831104e-06,
+      "loss": 0.4376,
+      "mean_token_accuracy": 0.8643449753522873,
+      "num_tokens": 110114714.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.7812703251838684,
+      "epoch": 0.08187772925764192,
+      "grad_norm": 0.494140625,
+      "learning_rate": 9.931115601017816e-06,
+      "loss": 0.4412,
+      "mean_token_accuracy": 0.8659342557191849,
+      "num_tokens": 117983612.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7815882682800293,
+      "epoch": 0.08733624454148471,
+      "grad_norm": 0.60546875,
+      "learning_rate": 9.915723254050551e-06,
+      "loss": 0.4264,
+      "mean_token_accuracy": 0.865845575928688,
+      "num_tokens": 125857638.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.7799684792757035,
+      "epoch": 0.0927947598253275,
+      "grad_norm": 0.71875,
+      "learning_rate": 9.898794518741725e-06,
+      "loss": 0.4217,
+      "mean_token_accuracy": 0.8657624512910843,
+      "num_tokens": 133718934.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.7746502578258514,
+      "epoch": 0.0982532751091703,
+      "grad_norm": 0.50390625,
+      "learning_rate": 9.880334686095365e-06,
+      "loss": 0.4375,
+      "mean_token_accuracy": 0.865676325559616,
+      "num_tokens": 141587252.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.7698926359415055,
+      "epoch": 0.1037117903930131,
+      "grad_norm": 0.87890625,
+      "learning_rate": 9.860349525653455e-06,
+      "loss": 0.4142,
+      "mean_token_accuracy": 0.8676840603351593,
+      "num_tokens": 149454258.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.7676965594291687,
+      "epoch": 0.1091703056768559,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.838845283692665e-06,
+      "loss": 0.4132,
+      "mean_token_accuracy": 0.8689810872077942,
+      "num_tokens": 157314466.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7642738163471222,
+      "epoch": 0.1146288209606987,
+      "grad_norm": 0.7265625,
+      "learning_rate": 9.815828681272127e-06,
+      "loss": 0.4098,
+      "mean_token_accuracy": 0.8706588715314865,
+      "num_tokens": 165182774.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.7638502717018127,
+      "epoch": 0.12008733624454149,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.791306912132776e-06,
+      "loss": 0.4081,
+      "mean_token_accuracy": 0.8702643483877182,
+      "num_tokens": 173042008.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.7644800752401352,
+      "epoch": 0.12554585152838427,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.765287640448996e-06,
+      "loss": 0.4065,
+      "mean_token_accuracy": 0.8699748694896698,
+      "num_tokens": 180901588.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.7578901439905167,
+      "epoch": 0.13100436681222707,
+      "grad_norm": 0.9453125,
+      "learning_rate": 9.737778998433198e-06,
+      "loss": 0.3974,
+      "mean_token_accuracy": 0.8707681357860565,
+      "num_tokens": 188769044.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.7537958860397339,
+      "epoch": 0.13646288209606988,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.708789583794144e-06,
+      "loss": 0.4011,
+      "mean_token_accuracy": 0.8707371085882187,
+      "num_tokens": 196634434.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.7602073311805725,
+      "epoch": 0.14192139737991266,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.678328457049766e-06,
+      "loss": 0.3991,
+      "mean_token_accuracy": 0.8711989611387253,
+      "num_tokens": 204486562.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.7597428560256958,
+      "epoch": 0.14737991266375547,
+      "grad_norm": 0.95703125,
+      "learning_rate": 9.646405138695331e-06,
+      "loss": 0.3997,
+      "mean_token_accuracy": 0.8710573464632034,
+      "num_tokens": 212351956.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.7577679485082627,
+      "epoch": 0.15283842794759825,
+      "grad_norm": 2.1875,
+      "learning_rate": 9.613029606227867e-06,
+      "loss": 0.399,
+      "mean_token_accuracy": 0.8701757520437241,
+      "num_tokens": 220205590.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.7598035603761673,
+      "epoch": 0.15829694323144106,
+      "grad_norm": 2.78125,
+      "learning_rate": 9.57821229102773e-06,
+      "loss": 0.4217,
+      "mean_token_accuracy": 0.8680002480745316,
+      "num_tokens": 228076474.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.7590495645999908,
+      "epoch": 0.16375545851528384,
+      "grad_norm": 2.578125,
+      "learning_rate": 9.541964075098313e-06,
+      "loss": 0.4285,
+      "mean_token_accuracy": 0.8676898956298829,
+      "num_tokens": 235936872.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.757094269990921,
+      "epoch": 0.16921397379912664,
+      "grad_norm": 2.359375,
+      "learning_rate": 9.50429628766494e-06,
+      "loss": 0.4185,
+      "mean_token_accuracy": 0.8680381834506988,
+      "num_tokens": 243803792.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.7542549550533295,
+      "epoch": 0.17467248908296942,
+      "grad_norm": 3.875,
+      "learning_rate": 9.465220701633953e-06,
+      "loss": 0.4055,
+      "mean_token_accuracy": 0.8681020706892013,
+      "num_tokens": 251674582.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.7625361144542694,
+      "epoch": 0.18013100436681223,
+      "grad_norm": 1.5,
+      "learning_rate": 9.424749529913138e-06,
+      "loss": 0.4199,
+      "mean_token_accuracy": 0.8669591844081879,
+      "num_tokens": 259538060.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.7554975986480713,
+      "epoch": 0.185589519650655,
+      "grad_norm": 0.68359375,
+      "learning_rate": 9.38289542159464e-06,
+      "loss": 0.4121,
+      "mean_token_accuracy": 0.8684647858142853,
+      "num_tokens": 267404072.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.7535371214151383,
+      "epoch": 0.19104803493449782,
+      "grad_norm": 0.8828125,
+      "learning_rate": 9.339671458001543e-06,
+      "loss": 0.3962,
+      "mean_token_accuracy": 0.8698400855064392,
+      "num_tokens": 275270380.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.754734218120575,
+      "epoch": 0.1965065502183406,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.295091148599353e-06,
+      "loss": 0.4112,
+      "mean_token_accuracy": 0.8690466344356537,
+      "num_tokens": 283145890.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.7563666641712189,
+      "epoch": 0.2019650655021834,
+      "grad_norm": 0.95703125,
+      "learning_rate": 9.249168426773675e-06,
+      "loss": 0.4091,
+      "mean_token_accuracy": 0.8709859728813172,
+      "num_tokens": 291005988.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.7565184265375138,
+      "epoch": 0.2074235807860262,
+      "grad_norm": 0.74609375,
+      "learning_rate": 9.201917645475393e-06,
+      "loss": 0.3981,
+      "mean_token_accuracy": 0.8720056504011154,
+      "num_tokens": 298864526.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.760869923233986,
+      "epoch": 0.212882096069869,
+      "grad_norm": 2.3125,
+      "learning_rate": 9.153353572734716e-06,
+      "loss": 0.4139,
+      "mean_token_accuracy": 0.869957122206688,
+      "num_tokens": 306735082.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.7582542330026627,
+      "epoch": 0.2183406113537118,
+      "grad_norm": 3.609375,
+      "learning_rate": 9.103491387045495e-06,
+      "loss": 0.4144,
+      "mean_token_accuracy": 0.8715152114629745,
+      "num_tokens": 314604158.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7573513597249985,
+      "epoch": 0.22379912663755458,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.052346672621246e-06,
+      "loss": 0.4132,
+      "mean_token_accuracy": 0.8716101557016372,
+      "num_tokens": 322465290.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.7590894103050232,
+      "epoch": 0.2292576419213974,
+      "grad_norm": 1.90625,
+      "learning_rate": 8.999935414524373e-06,
+      "loss": 0.417,
+      "mean_token_accuracy": 0.8695549905300141,
+      "num_tokens": 330336414.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.7527199715375901,
+      "epoch": 0.23471615720524017,
+      "grad_norm": 0.8359375,
+      "learning_rate": 8.9462739936701e-06,
+      "loss": 0.4077,
+      "mean_token_accuracy": 0.8720698267221451,
+      "num_tokens": 338189854.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.7517860412597657,
+      "epoch": 0.24017467248908297,
+      "grad_norm": 1.0859375,
+      "learning_rate": 8.891379181706697e-06,
+      "loss": 0.3975,
+      "mean_token_accuracy": 0.8719705253839493,
+      "num_tokens": 346051832.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.7506425231695175,
+      "epoch": 0.24563318777292575,
+      "grad_norm": 0.90625,
+      "learning_rate": 8.835268135773561e-06,
+      "loss": 0.4144,
+      "mean_token_accuracy": 0.8714013040065766,
+      "num_tokens": 353923892.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7511818319559097,
+      "epoch": 0.25109170305676853,
+      "grad_norm": 0.671875,
+      "learning_rate": 8.777958393138833e-06,
+      "loss": 0.3958,
+      "mean_token_accuracy": 0.8729292124509811,
+      "num_tokens": 361787270.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.7484469264745712,
+      "epoch": 0.25655021834061137,
+      "grad_norm": 1.234375,
+      "learning_rate": 8.719467865718192e-06,
+      "loss": 0.4055,
+      "mean_token_accuracy": 0.8726571470499038,
+      "num_tokens": 369659224.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.7491981714963913,
+      "epoch": 0.26200873362445415,
+      "grad_norm": 0.9375,
+      "learning_rate": 8.659814834476571e-06,
+      "loss": 0.3889,
+      "mean_token_accuracy": 0.8721846073865891,
+      "num_tokens": 377517650.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.745842233300209,
+      "epoch": 0.26746724890829693,
+      "grad_norm": 1.0,
+      "learning_rate": 8.599017943714514e-06,
+      "loss": 0.3995,
+      "mean_token_accuracy": 0.8731576293706894,
+      "num_tokens": 385374510.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.7489482790231705,
+      "epoch": 0.27292576419213976,
+      "grad_norm": 0.68359375,
+      "learning_rate": 8.537096195240982e-06,
+      "loss": 0.4032,
+      "mean_token_accuracy": 0.8717446327209473,
+      "num_tokens": 393229928.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7476549535989762,
+      "epoch": 0.27838427947598254,
+      "grad_norm": 2.046875,
+      "learning_rate": 8.47406894243441e-06,
+      "loss": 0.4009,
+      "mean_token_accuracy": 0.8734071612358093,
+      "num_tokens": 401092592.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.751323652267456,
+      "epoch": 0.2838427947598253,
+      "grad_norm": 1.0,
+      "learning_rate": 8.40995588419391e-06,
+      "loss": 0.3989,
+      "mean_token_accuracy": 0.8721231341361999,
+      "num_tokens": 408948350.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.7470169544219971,
+      "epoch": 0.2893013100436681,
+      "grad_norm": 1.8046875,
+      "learning_rate": 8.344777058782442e-06,
+      "loss": 0.3981,
+      "mean_token_accuracy": 0.8728294968605042,
+      "num_tokens": 416816292.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.7452338933944702,
+      "epoch": 0.29475982532751094,
+      "grad_norm": 1.1171875,
+      "learning_rate": 8.278552837563957e-06,
+      "loss": 0.3889,
+      "mean_token_accuracy": 0.8725773304700851,
+      "num_tokens": 424683528.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.7451816380023957,
+      "epoch": 0.3002183406113537,
+      "grad_norm": 2.28125,
+      "learning_rate": 8.211303918636403e-06,
+      "loss": 0.4006,
+      "mean_token_accuracy": 0.8727004051208496,
+      "num_tokens": 432547452.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.7443063974380493,
+      "epoch": 0.3056768558951965,
+      "grad_norm": 0.84765625,
+      "learning_rate": 8.143051320362632e-06,
+      "loss": 0.3947,
+      "mean_token_accuracy": 0.8734056413173675,
+      "num_tokens": 440414732.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.7448951125144958,
+      "epoch": 0.3111353711790393,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.07381637480119e-06,
+      "loss": 0.3892,
+      "mean_token_accuracy": 0.8715481579303741,
+      "num_tokens": 448281138.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.7429590493440628,
+      "epoch": 0.3165938864628821,
+      "grad_norm": 2.734375,
+      "learning_rate": 8.003620721039089e-06,
+      "loss": 0.3999,
+      "mean_token_accuracy": 0.8723650634288788,
+      "num_tokens": 456150890.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.7418043345212937,
+      "epoch": 0.3220524017467249,
+      "grad_norm": 0.7890625,
+      "learning_rate": 7.932486298428582e-06,
+      "loss": 0.3906,
+      "mean_token_accuracy": 0.8723206043243408,
+      "num_tokens": 464017298.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.7461079835891724,
+      "epoch": 0.32751091703056767,
+      "grad_norm": 1.5390625,
+      "learning_rate": 7.860435339730123e-06,
+      "loss": 0.4117,
+      "mean_token_accuracy": 0.8710065305233001,
+      "num_tokens": 471883034.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.742401072382927,
+      "epoch": 0.3329694323144105,
+      "grad_norm": 1.34375,
+      "learning_rate": 7.787490364163622e-06,
+      "loss": 0.3828,
+      "mean_token_accuracy": 0.8727285087108612,
+      "num_tokens": 479752180.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.7451883584260941,
+      "epoch": 0.3384279475982533,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.71367417037014e-06,
+      "loss": 0.3981,
+      "mean_token_accuracy": 0.8712346762418747,
+      "num_tokens": 487618472.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.742529284954071,
+      "epoch": 0.34388646288209607,
+      "grad_norm": 0.828125,
+      "learning_rate": 7.639009829286281e-06,
+      "loss": 0.3989,
+      "mean_token_accuracy": 0.8732034027576446,
+      "num_tokens": 495485140.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.7405054122209549,
+      "epoch": 0.34934497816593885,
+      "grad_norm": 0.65234375,
+      "learning_rate": 7.5635206769334715e-06,
+      "loss": 0.3937,
+      "mean_token_accuracy": 0.8724321722984314,
+      "num_tokens": 503352820.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.7433331936597825,
+      "epoch": 0.3548034934497817,
+      "grad_norm": 7.96875,
+      "learning_rate": 7.487230307124377e-06,
+      "loss": 0.4174,
+      "mean_token_accuracy": 0.8709851861000061,
+      "num_tokens": 511216636.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.7436719715595246,
+      "epoch": 0.36026200873362446,
+      "grad_norm": 4.375,
+      "learning_rate": 7.41016256408877e-06,
+      "loss": 0.4096,
+      "mean_token_accuracy": 0.870672419667244,
+      "num_tokens": 519092300.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.7409616202116013,
+      "epoch": 0.36572052401746724,
+      "grad_norm": 3.9375,
+      "learning_rate": 7.3323415350211035e-06,
+      "loss": 0.4065,
+      "mean_token_accuracy": 0.871986648440361,
+      "num_tokens": 526956202.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.7405611276626587,
+      "epoch": 0.37117903930131,
+      "grad_norm": 1.078125,
+      "learning_rate": 7.253791542552171e-06,
+      "loss": 0.4048,
+      "mean_token_accuracy": 0.8718220502138138,
+      "num_tokens": 534825720.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.7422936409711838,
+      "epoch": 0.37663755458515286,
+      "grad_norm": 2.6875,
+      "learning_rate": 7.1745371371471695e-06,
+      "loss": 0.4162,
+      "mean_token_accuracy": 0.870332533121109,
+      "num_tokens": 542689774.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.7440266788005829,
+      "epoch": 0.38209606986899564,
+      "grad_norm": 1.125,
+      "learning_rate": 7.094603089432554e-06,
+      "loss": 0.4026,
+      "mean_token_accuracy": 0.8710634887218476,
+      "num_tokens": 550546898.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.7456912964582443,
+      "epoch": 0.3875545851528384,
+      "grad_norm": 2.578125,
+      "learning_rate": 7.014014382454081e-06,
+      "loss": 0.4013,
+      "mean_token_accuracy": 0.869822895526886,
+      "num_tokens": 558414626.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.7425404369831086,
+      "epoch": 0.3930131004366812,
+      "grad_norm": 2.859375,
+      "learning_rate": 6.932796203868477e-06,
+      "loss": 0.3988,
+      "mean_token_accuracy": 0.8730183124542237,
+      "num_tokens": 566274998.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.7412711918354035,
+      "epoch": 0.39847161572052403,
+      "grad_norm": 0.87109375,
+      "learning_rate": 6.850973938071128e-06,
+      "loss": 0.3962,
+      "mean_token_accuracy": 0.8734320014715194,
+      "num_tokens": 574133032.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.7430791050195694,
+      "epoch": 0.4039301310043668,
+      "grad_norm": 2.46875,
+      "learning_rate": 6.7685731582623084e-06,
+      "loss": 0.4118,
+      "mean_token_accuracy": 0.8718510061502457,
+      "num_tokens": 582002578.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.744779172539711,
+      "epoch": 0.4093886462882096,
+      "grad_norm": 1.5390625,
+      "learning_rate": 6.685619618454372e-06,
+      "loss": 0.4077,
+      "mean_token_accuracy": 0.8716625690460205,
+      "num_tokens": 589865234.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.7440292358398437,
+      "epoch": 0.4148471615720524,
+      "grad_norm": 1.28125,
+      "learning_rate": 6.602139245422458e-06,
+      "loss": 0.4022,
+      "mean_token_accuracy": 0.8723435640335083,
+      "num_tokens": 597730534.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.7423117280006408,
+      "epoch": 0.4203056768558952,
+      "grad_norm": 2.71875,
+      "learning_rate": 6.518158130601188e-06,
+      "loss": 0.3945,
+      "mean_token_accuracy": 0.8720312714576721,
+      "num_tokens": 605595694.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.7398325890302658,
+      "epoch": 0.425764192139738,
+      "grad_norm": 0.8671875,
+      "learning_rate": 6.433702521929882e-06,
+      "loss": 0.4023,
+      "mean_token_accuracy": 0.874044144153595,
+      "num_tokens": 613453782.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.7427696764469147,
+      "epoch": 0.43122270742358076,
+      "grad_norm": 0.83984375,
+      "learning_rate": 6.348798815648904e-06,
+      "loss": 0.4091,
+      "mean_token_accuracy": 0.8732124745845795,
+      "num_tokens": 621320520.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.7425595790147781,
+      "epoch": 0.4366812227074236,
+      "grad_norm": 0.67578125,
+      "learning_rate": 6.2634735480496035e-06,
+      "loss": 0.3911,
+      "mean_token_accuracy": 0.8732421159744262,
+      "num_tokens": 629189244.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.7432102680206298,
+      "epoch": 0.4421397379912664,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.177753387180528e-06,
+      "loss": 0.4079,
+      "mean_token_accuracy": 0.8715735673904419,
+      "num_tokens": 637061832.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.7431057959794998,
+      "epoch": 0.44759825327510916,
+      "grad_norm": 0.98828125,
+      "learning_rate": 6.091665124512433e-06,
+      "loss": 0.4053,
+      "mean_token_accuracy": 0.8730859875679016,
+      "num_tokens": 644924166.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.7412999778985977,
+      "epoch": 0.45305676855895194,
+      "grad_norm": 2.046875,
+      "learning_rate": 6.0052356665647195e-06,
+      "loss": 0.3975,
+      "mean_token_accuracy": 0.8744613200426101,
+      "num_tokens": 652790794.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.7394814968109131,
+      "epoch": 0.4585152838427948,
+      "grad_norm": 0.875,
+      "learning_rate": 5.918492026495918e-06,
+      "loss": 0.4016,
+      "mean_token_accuracy": 0.8731278359889985,
+      "num_tokens": 660662846.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.7431211411952973,
+      "epoch": 0.46397379912663755,
+      "grad_norm": 1.0078125,
+      "learning_rate": 5.831461315660843e-06,
+      "loss": 0.4068,
+      "mean_token_accuracy": 0.8717893481254577,
+      "num_tokens": 668537662.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.7419637799263,
+      "epoch": 0.46943231441048033,
+      "grad_norm": 1.7734375,
+      "learning_rate": 5.744170735137053e-06,
+      "loss": 0.405,
+      "mean_token_accuracy": 0.8728329062461853,
+      "num_tokens": 676404470.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.7394852250814438,
+      "epoch": 0.47489082969432317,
+      "grad_norm": 0.90625,
+      "learning_rate": 5.6566475672232665e-06,
+      "loss": 0.3971,
+      "mean_token_accuracy": 0.874018257856369,
+      "num_tokens": 684267358.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.7418612122535706,
+      "epoch": 0.48034934497816595,
+      "grad_norm": 1.4765625,
+      "learning_rate": 5.568919166912403e-06,
+      "loss": 0.3945,
+      "mean_token_accuracy": 0.8733464300632476,
+      "num_tokens": 692133098.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.743475404381752,
+      "epoch": 0.48580786026200873,
+      "grad_norm": 0.62109375,
+      "learning_rate": 5.481012953341891e-06,
+      "loss": 0.4053,
+      "mean_token_accuracy": 0.872043314576149,
+      "num_tokens": 699998766.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.7418242216110229,
+      "epoch": 0.4912663755458515,
+      "grad_norm": 0.90625,
+      "learning_rate": 5.392956401223933e-06,
+      "loss": 0.4069,
+      "mean_token_accuracy": 0.8733739018440246,
+      "num_tokens": 707860696.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.7420300841331482,
+      "epoch": 0.49672489082969434,
+      "grad_norm": 1.40625,
+      "learning_rate": 5.304777032258407e-06,
+      "loss": 0.393,
+      "mean_token_accuracy": 0.8732639759778976,
+      "num_tokens": 715726050.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.7410448163747787,
+      "epoch": 0.5021834061135371,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.21650240653107e-06,
+      "loss": 0.4004,
+      "mean_token_accuracy": 0.8743464261293411,
+      "num_tokens": 723597802.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.7398734450340271,
+      "epoch": 0.50764192139738,
+      "grad_norm": 1.25,
+      "learning_rate": 5.128160113899775e-06,
+      "loss": 0.3923,
+      "mean_token_accuracy": 0.8746407985687256,
+      "num_tokens": 731470234.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.7414282083511352,
+      "epoch": 0.5131004366812227,
+      "grad_norm": 3.0,
+      "learning_rate": 5.0397777653713775e-06,
+      "loss": 0.3814,
+      "mean_token_accuracy": 0.874212983250618,
+      "num_tokens": 739340274.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.7401980370283127,
+      "epoch": 0.5185589519650655,
+      "grad_norm": 1.3828125,
+      "learning_rate": 4.951382984472033e-06,
+      "loss": 0.3949,
+      "mean_token_accuracy": 0.8753201216459274,
+      "num_tokens": 747205480.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.7414378315210343,
+      "epoch": 0.5240174672489083,
+      "grad_norm": 1.1015625,
+      "learning_rate": 4.86300339861358e-06,
+      "loss": 0.3825,
+      "mean_token_accuracy": 0.8729045927524567,
+      "num_tokens": 755074202.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.7381639093160629,
+      "epoch": 0.5294759825327511,
+      "grad_norm": 0.6875,
+      "learning_rate": 4.774666630458711e-06,
+      "loss": 0.3976,
+      "mean_token_accuracy": 0.875198820233345,
+      "num_tokens": 762934560.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.7392808586359024,
+      "epoch": 0.5349344978165939,
+      "grad_norm": 1.1640625,
+      "learning_rate": 4.686400289287634e-06,
+      "loss": 0.3904,
+      "mean_token_accuracy": 0.8743301123380661,
+      "num_tokens": 770791148.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.739506584405899,
+      "epoch": 0.5403930131004366,
+      "grad_norm": 0.90234375,
+      "learning_rate": 4.598231962368897e-06,
+      "loss": 0.3959,
+      "mean_token_accuracy": 0.8746915906667709,
+      "num_tokens": 778655538.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.737652936577797,
+      "epoch": 0.5458515283842795,
+      "grad_norm": 1.109375,
+      "learning_rate": 4.510189206337115e-06,
+      "loss": 0.3862,
+      "mean_token_accuracy": 0.8748303711414337,
+      "num_tokens": 786523130.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1832,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.793915569764827e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0a9d4160eb0c48031f9d2186009a014dffa64d47715a7a879034c6fa10973a
+size 6481

checkpoint-1000/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"
+}

checkpoint-1500/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
+}

checkpoint-1500/chat_template.jinja

@@ -0,0 +1,110 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- else %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                <|vision_start|><|image_pad|><|vision_end|>
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                <|vision_start|><|video_pad|><|vision_end|>
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{%- endmacro %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- render_content(messages[0].content, false) + '\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' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false) %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, True) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and 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' }}
+        {{- content }}
+        {{- '\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 %}

checkpoint-1500/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

checkpoint-1500/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:882379508910d25fc6c2e7a1bb6fe6a9d987b7c46500219fbd740c674cf375ef
+size 4990497880

checkpoint-1500/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ad17817ca4c28c8bc0e86b060c5b99acb7a677ccb35a513d5736819f3509a6
+size 3885221448

checkpoint-1500/model.safetensors.index.json

@@ -0,0 +1,721 @@
+{
+  "metadata": {
+    "total_parameters": 4437815808,
+    "total_size": 8875631616
+  },
+  "weight_map": {
+    "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+  }
+}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a962d70ed31d9cfe7a678e08bc1b14089840754da6ab70cc46d5fdefff3963c2
+size 17751894342

checkpoint-1500/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
+}

checkpoint-1500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478b41e9f26d338fd8f896e08cad1adab7c423b61f1b45754113bc78d256a3f9
+size 16389

checkpoint-1500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce29a8767a7d907dd24987aa2c3e654d4317f3042fbc13b5b72cadb46d43311a
+size 16389

checkpoint-1500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a48db011646b4e9a867bf12f4a233cad5dfbfe309686f8996c250196d3783a
+size 16389

checkpoint-1500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9562ee822472a4f01dcd6349ab3d1ef42a48915fe3b92e843a0c37db53c8421
+size 16389

checkpoint-1500/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d2767d83c3bf27f12db022b0632e2c4f8c164274ba75e380cf18f9d5f21819
+size 16389

checkpoint-1500/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76816358d4e5db8149d60d55234db658d67a13c0c1ce05d7404cf7125a676a5c
+size 16389

checkpoint-1500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1562e7520c977d178183d641f70abcf3f57da2489938756cfbebf9b6e6c1a9fd
+size 16389

checkpoint-1500/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b6cabaed045c5398cd1b732f7ec48bd363f3b43cd24e0e70e641a42bd00c28
+size 16389

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6fc75076163e098ebb6c8025fd34ed42d5995f3c7c37b29414d9b97a6190c3
+size 1465

checkpoint-1500/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
+  }
+}