Upload README.md with huggingface_hub

README.md

@@ -17,7 +17,7 @@ library_name: transformers
 
 **CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward**
 
-[![arXiv](https://img.shields.io/badge/arXiv-2505.19713-b31b1b.svg)](https://arxiv.org/abs/2505.19713)
+This is the reinforcement learning (GRPO) fine-tuned model for generating CadQuery code from natural language descriptions.
 
 ## Model Description
 
@@ -31,9 +31,21 @@ CAD-Coder reformulates text-to-CAD as the generation of CadQuery scripts—a Pyt
 - 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
 
@@ -41,20 +53,16 @@ model_name = "gudo7208/CAD-Coder"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
 
-# Example prompt
-prompt = """Create a cylinder with radius 10mm and height 20mm, with a central hole of radius 5mm."""
-
-messages = [
-    {"role": "system", "content": "You are a helpful assistant."},
-    {"role": "user", "content": prompt}
-]
+prompt = "Create a cylinder with radius 10mm and height 20mm, with a central hole of radius 5mm."
 
-text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+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=512, temperature=0.7, top_p=0.8, top_k=20)
-response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
-print(response)
+outputs = model.generate(**inputs, max_new_tokens=2048)
+print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
 ```
 
 ## Performance
@@ -90,8 +98,5 @@ This model is released under the Apache 2.0 License, following the base model (Q
 
 ## Acknowledgements
 
-We thank the following works for their contributions:
-
-- [Qwen2.5](https://github.com/QwenLM/Qwen2.5) - Base model for CAD-Coder
-- [Text2CAD](https://github.com/sadilkhan/Text2CAD) - Text-to-CAD dataset and benchmark
-- [DeepCAD](https://github.com/ChrisWu1997/DeepCAD) - Pioneering work on deep generative models for CAD
+- 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