CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward This is the reinforcement learning (GRPO) fine-tuned model for generating CadQuery code from natural language descriptions. CAD-Coder reformulates text-to-CAD as the generation of CadQuery scripts—a Python-based, parametric CAD language. The model is trained with a two-stage pipeline: 1. Supervised Fine-Tuning (SFT): Learning CadQuery syntax and text-to-code mapping 2. Reinforcement Learning (GRPO): Optimizing geometric accuracy with CAD-specific rewards (Chamfer Distance + Format Reward) — Generates executable CadQuery Python code from natural language — Chain-of-Thought (CoT) reasoning for complex CAD structures — Geometric reward optimization for accurate 3D model generation — Supports diverse CAD operations beyond simple sketch-extrusion For complete inference scripts, please visit our GitHub repository. — Base Model: Qwen2.5-7B-Instruct — Training Data: 110K text-CadQuery-3D model triplets + 1.5K CoT samples — Hardware: 8× NVIDIA A800 80GB GPUs — Framework: Hugging Face Transformers, DeepSpeed, Verl (GRPO) This model is released under the Apache 2.0 License, following the base model…
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Задача: Генерация текста
Автор: gudo7208
Теги: qwen2, text-to-cad, code-generation, cadquery, 3d-modeling, reinforcement-learning, conversational, en
Лайков: 3 | Загрузок: 464
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
