| --- |
| base_model: |
| - Qwen/Qwen2.5-Coder-14B-Instruct |
| datasets: |
| - TIGER-Lab/VisCode-Multi-679K |
| language: |
| - en |
| license: apache-2.0 |
| tags: |
| - code |
| pipeline_tag: image-text-to-text |
| library_name: transformers |
| --- |
| |
| # VisCoder2-14B |
|
|
| [🏠 Project Page](https://tiger-ai-lab.github.io/VisCoder2) | [📖 Paper](https://arxiv.org/abs/2510.23642) | [💻 GitHub](https://github.com/TIGER-AI-Lab/VisCoder2) | [🤗 VisCode2](https://hf.co/collections/TIGER-Lab/viscoder2) |
|
|
| **VisCoder2-14B** is a lightweight multi-language visualization coding model trained for **executable code generation, rendering, and iterative self-debugging**. |
|
|
| --- |
|
|
| ## 🧠 Model Description |
|
|
| **VisCoder2-14B** 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 VisCoder2-14B on [**VisPlotBench**](https://huggingface.co/datasets/TIGER-Lab/VisPlotBench), which includes 888 executable visualization tasks spanning 8 languages, supporting both standard generation and multi-turn self-debugging. |
|
|
|  |
|
|
| > **VisCoder2-14B** shows consistent performance across multiple languages and achieves notable improvements under the multi-round self-debug setting. |
| --- |
|
|
| ## 📁 Training Details |
|
|
| - **Base model**: Qwen2.5-Coder-14B-Instruct |
| - **Framework**: [ms-swift](https://github.com/modelscope/swift) |
| - **Tuning method**: Full-parameter supervised fine-tuning (SFT) |
| - **Dataset**: [VisCode-Multi-679K](https://huggingface.co/datasets/TIGER-Lab/VisCode-Multi-679K) |
|
|
| --- |
|
|
| ## 📖 Citation |
|
|
| If you use VisCoder2-14B or related datasets in your research, please cite: |
|
|
| ```bibtex |
| @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](https://github.com/TIGER-AI-Lab/VisCoder2). |
