🏠 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. 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. 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…
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Задача: Генерация текста
Автор: TIGER-Lab
Теги: qwen2, code, conversational, en, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 32
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
