Instructions to use gogoduan/CodePlot-CoT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gogoduan/CodePlot-CoT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="gogoduan/CodePlot-CoT")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("gogoduan/CodePlot-CoT")
model = AutoModelForImageTextToText.from_pretrained("gogoduan/CodePlot-CoT")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gogoduan/CodePlot-CoT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gogoduan/CodePlot-CoT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gogoduan/CodePlot-CoT",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/gogoduan/CodePlot-CoT

SGLang

How to use gogoduan/CodePlot-CoT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "gogoduan/CodePlot-CoT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gogoduan/CodePlot-CoT",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "gogoduan/CodePlot-CoT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gogoduan/CodePlot-CoT",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use gogoduan/CodePlot-CoT with Docker Model Runner:
```
docker model run hf.co/gogoduan/CodePlot-CoT
```

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

This repository contains the CodePlot-CoT model, a core component of the paper CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images. CodePlot-CoT is an innovative code-driven Chain-of-Thought (CoT) paradigm designed to enable Vision Language Models (VLMs) to "think with images" when solving mathematical problems. Instead of generating pixel-based images directly, the model outputs executable plotting code to represent its "visual thoughts". This code is then executed to render a precise figure, which is reinput to the model as a visual input for subsequent reasoning steps.

The model is built upon the Qwen2.5-VL architecture and is compatible with the transformers library.

For more details, please refer to the project homepage and the GitHub repository.

Citation

If you find this work helpful, please consider citing our paper:

@article{duan2025codeplot,
  title={CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images},
  author={Duan, Chengqi and Sun, Kaiyue and Fang, Rongyao and Zhang, Manyuan and Feng, Yan and Luo, Ying and Liu, Yufang and Wang, Ke and Pei, Peng and Cai, Xunliang and others},
  journal={arXiv preprint arXiv:2510.11718},
  year={2025}
}

Downloads last month: 32

Safetensors

Model size

33B params

Tensor type

BF16

Paper for gogoduan/CodePlot-CoT

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

Paper • 2510.11718 • Published Oct 13, 2025 • 14