Safetensors
English
qwen2
code

VisCoder-7B

🏠 Project Page | πŸ“– Paper | πŸ’» GitHub | πŸ€— VisCode-200K | πŸ€— VisCoder-3B

VisCoder-7B is a large language model fine-tuned for Python visualization code generation and multi-turn self-correction. It is trained on VisCode-200K, a large-scale instruction-tuning dataset that integrates validated executable code, natural language instructions, and revision supervision from execution feedback.

🧠 Model Description

VisCoder-7B 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.

πŸ“Š Main Results on PandasPlotBench

We evaluate VisCoder-7B on PandasPlotBench, which tests executable visualization code generation across three major libraries. Our benchmark covers both standard generation and multi-round self-debugging.

image/png

VisCoder-7B achieves over 90% execution pass rate on both Matplotlib and Seaborn under the self-debug setting, outperforming open-source baselines and approaching GPT-4o performance.

πŸ“ Training Details

  • Base model: Qwen2.5-Coder-7B-Instruct
  • Framework: ms-swift
  • Tuning method: Full-parameter supervised fine-tuning (SFT)
  • Dataset: VisCode-200K, which includes:
    • 150K+ validated Python visualization samples with images
    • 45K+ multi-turn correction dialogues with execution feedback

πŸ“– Citation

If you use VisCoder-7B or VisCode-200K in your research, please cite:

@misc{ni2025viscoderfinetuningllmsexecutable,
      title={VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation}, 
      author={Yuansheng Ni and Ping Nie and Kai Zou and Xiang Yue and Wenhu Chen},
      year={2025},
      eprint={2506.03930},
      archivePrefix={arXiv},
      primaryClass={cs.SE},
      url={https://arxiv.org/abs/2506.03930}
}

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

Downloads last month
25
Safetensors
Model size
7.62B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for TIGER-Lab/VisCoder-7B

Base model

Qwen/Qwen2.5-7B
Finetuned
(150)
this model
Quantizations
1 model

Dataset used to train TIGER-Lab/VisCoder-7B

Collection including TIGER-Lab/VisCoder-7B