VisCoder2-7B
🏠 Project Page | 📖 Paper | 💻 GitHub | 🤗 VisCode2
VisCoder2-7B is a lightweight multi-language visualization coding model trained for executable code generation, rendering, and iterative self-debugging.
🧠 Model Description
VisCoder2-7B is trained on the VisCode-Multi-679K dataset, a large-scale instruction-tuning dataset for executable visualization tasks across 12 programming language. It addresses a core challenge in multi-language visualization: generating code that not only executes successfully but also produces semantically consistent visual outputs by aligning natural-language instructions and rendering results.
📊 Main Results on VisPlotBench
We evaluate VisCoder2-7B on VisPlotBench, which includes 888 executable visualization tasks spanning 8 languages, supporting both standard generation and multi-turn self-debugging.
VisCoder2-7B shows consistent performance across multiple languages and achieves notable improvements under the multi-round self-debug setting.
📁 Training Details
- Base model: Qwen2.5-Coder-7B-Instruct
- Framework: ms-swift
- Tuning method: Full-parameter supervised fine-tuning (SFT)
- Dataset: VisCode-Multi-679K
📖 Citation
If you use VisCoder2-7B or related datasets in your research, please cite:
@article{ni2025viscoder2,
title={VisCoder2: Building Multi-Language Visualization Coding Agents},
author={Ni, Yuansheng and Cai, Songcheng and Chen, Xiangchao and Liang, Jiarong and Lyu, Zhiheng and Deng, Jiaqi and Zou, Kai and Nie, Ping and Yuan, Fei and Yue, Xiang and others},
journal={arXiv preprint arXiv:2510.23642},
year={2025}
}
@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.