Duplicate from ThinkMorph/ThinkMorph-7B

Co-authored-by: Yunzhuo Hao <luckychao@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,96 @@
+---
+license: apache-2.0
+base_model:
+- ByteDance-Seed/BAGEL-7B-MoT
+pipeline_tag: any-to-any
+library_name: ThinkMorph-7B
+---
+
+<p align="center">
+    <img src="https://github.com/ThinkMorph/ThinkMorph/raw/main/assets/logo.png" width="40%"> <br>
+</p>
+
+
+## Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
+
+
+
+<p align="center">
+  <a href="https://thinkmorph.github.io/">
+    <img
+      src="https://img.shields.io/badge/ThinkMorph-Website-0A66C2?logo=safari&logoColor=white"
+      alt="ThinkMorph Website"
+    />
+  </a>
+  <a href="https://arxiv.org/abs/2510.27492">
+    <img
+      src="https://img.shields.io/badge/ThinkMorph-Paper-red?logo=arxiv&logoColor=red"
+      alt="ThinkMorph Paper on arXiv"
+    />
+  </a>
+  <a href="https://github.com/ThinkMorph/ThinkMorph">
+      <img 
+        alt="Github" src="https://img.shields.io/badge/ThinkMorph-Codebase-536af5?color=536af5&logo=github"
+        alt="ThinkMorph Codebase"
+      />
+  </a>
+  <a href="https://huggingface.co/ThinkMorph">
+    <img 
+        src="https://img.shields.io/badge/ThinkMorph-Dataset-yellow?logo=huggingface&logoColor=yellow" 
+        alt="ThinkMorph Dataset"
+    />
+  </a>
+  <!-- <a href="https://demo.bagel-ai.org/">
+    <img
+      src="https://img.shields.io/badge/BAGEL-Demo-blue?logo=googleplay&logoColor=blue"
+      alt="BAGEL Demo"
+    />
+  </a> -->
+</p>
+
+
+## 👀 About ThinkMorph
+
+<p align="center">
+    <img src="https://github.com/ThinkMorph/ThinkMorph/raw/main/assets/thinkmorph.jpg" width="100%"> <br>
+</p>
+
+We present **ThinkMorph**, a unified model fine-tuned on ∼24K high-quality interleaved reasoning traces across tasks, learning to generate progressive text–image reasoning steps that
+concretely manipulate visual content while maintaining coherent verbal logic.
+
+Beyond strong vision-benchmark performance and robust out-of-domain generalization, ThinkMorph demonstrates emergent multimodal intelligence, including novel visual manipulation skills and so on.
+These findings suggest promising directions for characterizing the emergent capabilities of unified models for multimodal reasoning.
+
+
+
+## 📊 Benchmarks
+
+| Model | Size |  | VSP | VisPuzzle | ChartQA | VStar | BLINK-J | MMVP | SAT | BLINK | CV-Bench |
+| --- | --- | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| GPT-4o | – |  | 33.50 | 43.75 | 76.34 | 61.78 | 72.67 | 84.67 | 28.00 | 60.28 | 75.61 |
+| GPT-5 | – |  | 57.33 | 78.00 | 80.85 | 71.73 | 77.33 | 86.33 | 73.30 | 69.86 | 85.46 |
+| Gemini 2.5 Flash | – |  | 59.33 | 47.00 | 83.79 | 70.68 | 66.00 | 80.33 | 56.00 | 67.49 | 85.07 |
+| InternVL3.5 | 8B |  | 8.17 | 34.75 | 76.26 | 68.59 | 71.33 | 76.33 | 45.33 | 59.60 | 81.99 |
+|  | 38B |  | 20.16 | 36.50 | 80.44 | 76.96 | 80.67 | 80.33 | 49.33 | 62.65 | 85.96 |
+| Qwen2.5-VL | 7B |  | 2.16 | 34.75 | 78.12 | 76.44 | 59.33 | 77.33 | 51.33 | 55.92 | 75.20 |
+|  | 72B |  | 41.83 | 40.00 | 82.03 | 85.86 | 61.33 | 82.00 | 64.67 | 61.91 | 82.54 |
+| Janus-pro | 7B |  | 0.00 | 33.50 | 43.08 | 38.22 | 50.67 | 63.33 | 22.00 | 38.51 | 67.83 |
+| Chameleon | 7B |  | 0.83 | 30.50 | 5.74 | 28.27 | 0.67 | 47.67 | 10.67 | 16.52 | 36.52 |
+| Bagel | 7B |  | 0.83* | 35.00* | 61.82 | 55.49 | 67.33 | 70.33 | 44.67 | 47.66 | 76.03 |
+| **ThinkMorph** | **7B** |  | **75.83** | **79.00** | **78.10** | **67.02** | **72.00** | **80.33** | **52.67** | **60.07** | **80.82** |
+| Δ (vs Bagel) |  |  | +75.00 | +44.00 | +16.28 | +11.53 | +4.67 | +10.00 | +8.00 | +12.41 | +4.79 |
+
+
+## ✍️ Citation
+
+```bibtex
+@misc{gu2025thinkmorphemergentpropertiesmultimodal,
+      title={ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning}, 
+      author={Jiawei Gu and Yunzhuo Hao and Huichen Will Wang and Linjie Li and Michael Qizhe Shieh and Yejin Choi and Ranjay Krishna and Yu Cheng},
+      year={2025},
+      eprint={2510.27492},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2510.27492}, 
+}
+```

ae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+size 335304388

config.json

@@ -0,0 +1,5 @@
+{
+  "name": [
+    "BAGEL-7B-MoT"
+  ],
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

llm_config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c05fc7d7feefd429d4c0c642bd4296b69ebc11c556f525bc913ed0d9c22b414
+size 29214685336

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

vit_config.json

@@ -0,0 +1,9 @@
+{
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+}