105 lines
3.2 KiB
Markdown
105 lines
3.2 KiB
Markdown
|
---
|
|||
|
|
license: apache-2.0
|
|||
|
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
|||
|
|
tags:
|
|||
|
|
- text-to-cad
|
|||
|
|
- code-generation
|
|||
|
|
- cadquery
|
|||
|
|
- 3d-modeling
|
|||
|
|
- reinforcement-learning
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
library_name: transformers
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# CAD-Coder
|
|||
|
|
|
|||
|
|
**CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward**
|
|||
|
|
|
|||
|
|
**Accepted at NeurIPS 2025 (Poster)**
|
|||
|
|
|
|||
|
|
This is the reinforcement learning (GRPO) fine-tuned model for generating CadQuery code from natural language descriptions.
|
|||
|
|
|
|||
|
|
## Model Description
|
|||
|
|
|
|||
|
|
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)
|
|||
|
|
|
|||
|
|
### Key Features
|
|||
|
|
|
|||
|
|
- 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
|
|||
|
|
|
|||
|
|
## Usage
|
|||
|
|
|
|||
|
|
For complete inference scripts, please visit our [GitHub repository](https://github.com/gudo7208/CAD-Coder).
|
|||
|
|
|
|||
|
|
### Installation
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
pip install transformers
|
|||
|
|
pip install "numpy<2.0" cadquery==2.3.1 # Optional: for code execution
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### Quick Start
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|||
|
|
|
|||
|
|
model_name = "gudo7208/CAD-Coder"
|
|||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|||
|
|
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
|
|||
|
|
|
|||
|
|
prompt = "Create a cylinder with radius 10mm and height 20mm, with a central hole of radius 5mm."
|
|||
|
|
|
|||
|
|
text = tokenizer.apply_chat_template(
|
|||
|
|
[{"role": "user", "content": prompt}],
|
|||
|
|
tokenize=False,
|
|||
|
|
add_generation_prompt=True
|
|||
|
|
)
|
|||
|
|
inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
|||
|
|
outputs = model.generate(**inputs, max_new_tokens=2048)
|
|||
|
|
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## Performance
|
|||
|
|
|
|||
|
|
| Method | Mean CD | Median CD | IR% |
|
|||
|
|
|--------|---------|-----------|-----|
|
|||
|
|
| Text2CAD | 29.29 | 0.37 | 3.75 |
|
|||
|
|
| **CAD-Coder (Ours)** | **6.54** | **0.17** | **1.45** |
|
|||
|
|
|
|||
|
|
*CD metrics are ×10³. Lower is better.*
|
|||
|
|
|
|||
|
|
## Training Details
|
|||
|
|
|
|||
|
|
- **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)
|
|||
|
|
|
|||
|
|
## Citation
|
|||
|
|
|
|||
|
|
```bibtex
|
|||
|
|
@article{guan2025cadcoder,
|
|||
|
|
title={CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward},
|
|||
|
|
author={Guan, Yandong and Wang, Xilin and Xing, Ximing and Zhang, Jing and Xu, Dong and Yu, Qian},
|
|||
|
|
journal={arXiv preprint arXiv:2505.19713},
|
|||
|
|
year={2025}
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## License
|
|||
|
|
|
|||
|
|
This model is released under the Apache 2.0 License, following the base model (Qwen2.5-7B-Instruct) license terms.
|
|||
|
|
|
|||
|
|
## Acknowledgements
|
|||
|
|
|
|||
|
|
- Base model: [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
|
|||
|
|
- Training data derived from [Text2CAD](https://github.com/sadilkhan/Text2CAD) dataset
|