Instructions to use TIGER-Lab/VisCoder-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TIGER-Lab/VisCoder-3B with Transformers:

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

pipe = pipeline("text-generation", model="TIGER-Lab/VisCoder-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TIGER-Lab/VisCoder-3B")
model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/VisCoder-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TIGER-Lab/VisCoder-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/VisCoder-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/VisCoder-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TIGER-Lab/VisCoder-3B

SGLang

How to use TIGER-Lab/VisCoder-3B 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 "TIGER-Lab/VisCoder-3B" \
    --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": "TIGER-Lab/VisCoder-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "TIGER-Lab/VisCoder-3B" \
        --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": "TIGER-Lab/VisCoder-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TIGER-Lab/VisCoder-3B with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/VisCoder-3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

VisCoder-3B

🏠 Project Page | 📖 Paper | 💻 GitHub | 🤗 VisCode-200K | 🤗 VisCoder-7B

VisCoder-3B is a lightweight language model fine-tuned for Python visualization code generation and iterative correction. It is trained on VisCode-200K, a large-scale instruction-tuning dataset that integrates natural language instructions, validated Python code, and execution-guided revision supervision.

🧠 Model Description

VisCoder-3B is trained on VisCode-200K, a large-scale instruction-tuning dataset tailored for executable Python visualization tasks. It addresses a core challenge in data analysis: generating Python code that not only executes successfully but also produces semantically meaningful plots by aligning natural language instructions, data structures, and visual outputs.

We propose a self-debug evaluation protocol that simulates real-world developer workflows. In this setting, models are allowed to revise previously failed generations over multiple rounds with guidance from execution feedback.

📊 Main Results on PandasPlotBench

We evaluate VisCoder-3B on PandasPlotBench, which tests executable visualization code generation across Matplotlib, Seaborn, and Plotly. Evaluation includes both standard generation and multi-turn self-debugging

VisCoder-3B outperforms existing open-source baselines on multiple libraries and shows consistent recovery improvements under the self-debug protocol.

📁 Training Details

Base model: Qwen2.5-Coder-3B-Instruct
Framework: ms-swift
Tuning method: Full-parameter supervised fine-tuning (SFT)
Dataset: VisCode-200K, which includes:
- 150K+ validated Python visualization samples with corresponding images
- 45K+ multi-turn correction dialogues guided by execution results

📖 Citation

If you use VisCoder-3B or VisCode-200K in your research, please cite:

@article{ni2025viscoder,
  title={VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation},
  author={Ni, Yuansheng and Nie, Ping and Zou, Kai and Yue, Xiang and Chen, Wenhu},
  journal={arXiv preprint arXiv:2506.03930},
  year={2025}
}

For evaluation scripts and more information, see our GitHub repository.