TIGER-Lab / VisCoder2-14B

huggingface.co
Total runs: 21
24-hour runs: 0
7-day runs: 5
30-day runs: -69
Model's Last Updated: November 04 2025
image-text-to-text

Introduction of VisCoder2-14B

Model Details of VisCoder2-14B

VisCoder2-14B

🏠 Project Page | 📖 Paper | 💻 GitHub | 🤗 VisCode2

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 , which includes 888 executable visualization tasks spanning 8 languages, supporting both standard generation and multi-turn self-debugging.

main_results

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
  • Tuning method : Full-parameter supervised fine-tuning (SFT)
  • Dataset : VisCode-Multi-679K

📖 Citation

If you use VisCoder2-14B or related datasets in your research, please cite:

@misc{ni2025viscoder2buildingmultilanguagevisualization,
      title={VisCoder2: Building Multi-Language Visualization Coding Agents}, 
      author={Yuansheng Ni and Songcheng Cai and Xiangchao Chen and Jiarong Liang and Zhiheng Lyu and Jiaqi Deng and Kai Zou and Ping Nie and Fei Yuan and Xiang Yue and Wenhu Chen},
      year={2025},
      eprint={2510.23642},
      archivePrefix={arXiv},
      primaryClass={cs.SE},
      url={https://arxiv.org/abs/2510.23642}, 
}

@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 .

Runs of TIGER-Lab VisCoder2-14B on huggingface.co

21
Total runs
0
24-hour runs
0
3-day runs
5
7-day runs
-69
30-day runs

More Information About VisCoder2-14B huggingface.co Model

More VisCoder2-14B license Visit here:

https://choosealicense.com/licenses/apache-2.0

VisCoder2-14B huggingface.co

VisCoder2-14B huggingface.co is an AI model on huggingface.co that provides VisCoder2-14B's model effect (), which can be used instantly with this TIGER-Lab VisCoder2-14B model. huggingface.co supports a free trial of the VisCoder2-14B model, and also provides paid use of the VisCoder2-14B. Support call VisCoder2-14B model through api, including Node.js, Python, http.

VisCoder2-14B huggingface.co Url

https://huggingface.co/TIGER-Lab/VisCoder2-14B

TIGER-Lab VisCoder2-14B online free

VisCoder2-14B huggingface.co is an online trial and call api platform, which integrates VisCoder2-14B's modeling effects, including api services, and provides a free online trial of VisCoder2-14B, you can try VisCoder2-14B online for free by clicking the link below.

TIGER-Lab VisCoder2-14B online free url in huggingface.co:

https://huggingface.co/TIGER-Lab/VisCoder2-14B

VisCoder2-14B install

VisCoder2-14B is an open source model from GitHub that offers a free installation service, and any user can find VisCoder2-14B on GitHub to install. At the same time, huggingface.co provides the effect of VisCoder2-14B install, users can directly use VisCoder2-14B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

VisCoder2-14B install url in huggingface.co:

https://huggingface.co/TIGER-Lab/VisCoder2-14B

Url of VisCoder2-14B

VisCoder2-14B huggingface.co Url

Provider of VisCoder2-14B huggingface.co

TIGER-Lab
ORGANIZATIONS

Other API from TIGER-Lab

huggingface.co

Total runs: 2.9K
Run Growth: 2.5K
Growth Rate: 86.16%
Updated:October 14 2025
huggingface.co

Total runs: 899
Run Growth: 716
Growth Rate: 81.00%
Updated:December 06 2023
huggingface.co

Total runs: 847
Run Growth: 719
Growth Rate: 87.90%
Updated:December 06 2023
huggingface.co

Total runs: 499
Run Growth: -975
Growth Rate: -195.39%
Updated:January 09 2025
huggingface.co

Total runs: 10
Run Growth: -12
Growth Rate: -120.00%
Updated:December 06 2023
huggingface.co

Total runs: 5
Run Growth: -28
Growth Rate: -560.00%
Updated:April 04 2024