Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
BlenderLLM: A LLM specifically designed to generate CAD scripts based on user instructions. These scripts are then executed in Blender to render 3D models.
| Date | Stars |
|---|---|
| 2026-07-31 | 278 |
| 2026-08-06 | 278 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<!-- <div align="center">
<img src="assets/icon.svg" width="40" alt="Problem Definition" style="vertical-align: middle;"/>
<span style="font-size: 24px; font-weight: bold;">BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement</span>
</div> -->
# BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement
## ✨ Latest News
<!-- - [12/11/2023]: 🎉🎉🎉 Our paper is accepted for EMNLP 2023! Check it out [here](https://aclanthology.org/2023.findings-emnlp.725/).
- [11/25/2023]: We realeased **[HuatuoGPT-II](https://github.com/FreedomIntelligence/HuatuoGPT-II)**, which achieved a new state-of-the-art in Chinese medical applications! See [here](https://github.com/FreedomIntelligence/HuatuoGPT-II).
- [09/26/2023]: Release [HuatuoGPT-reward-model](https://huggingface.co/FreedomIntelligence/HuatuoGPT-reward-model-7B). -->
- [12/17/2024]: Release the `<instruction, bpy script>` dataset: [BlenderNet](https://huggingface.co/datasets/FreedomIntelligence/BlendNet) and the benchmark: [CADBench](https://huggingface.co/datasets/FreedomIntelligence/CADBench).
- [12/17/2024]: Release the model weights of [BlenderLLM](https://huggingface.co/FreedomIntelligence/BlenderLLM).
- [12/16/2024]: Release the [tech report](https://www.arxiv.org/abs/2412.14203).
## ⚡ Introduction
<div align=center>
<img src="assets/definition.png" width = "640" alt="Problem Definition" align=center/>
</div>
Welcome to the repository of **BlenderLLM**. **BlenderLLM** is a large language model specifically designed to generate CAD scripts based on user instructions. These scripts are then executed in Blender to render 3D models.
Here is a list of what has been released:
1. **BlendNet**: A high-quality dataset containing $12k$ `<instruction, CAD script>` pairs.
2. **BlenderLLM**: A large language model fine-tuned on BlendNet based on **Qwen2.5-Coder-7B-Instruct**, designed to output CAD scripts.
3. **CADBench**: A comprehensive benchmark for evaluating this task.
<div align=center>
<img src="assets/framework.png" width = "640" alt="Pipeline" align=center/>
</div>
## 💭 Motivation
- To address the challenges posed by the complexity of input forms in CAD applications. We recognize that the high threshold for use limits accessibility, and we believe that user-friendly interfaces and simplified input methods are essential to encourage wider adoption of CAD-oriented LLMs.
- To provide high-quality, domain-specific datasets for training CAD-oriented LLMs. Building datasets that capture the intricate nuances of CAD design is critical, yet challenging. Efforts to create and share such datasets will significantly enhance the ability of LLMs to understand and perform CAD tasks effectively.
- To ensure accessibility, local deployment, and privacy preservation through open-source CAD-oriented LLMs. By developing and releasing open-source models, we aim to democratize access to advanced tools, empower localized and secure deployments, and support diverse user needs in the CAD domain.
- To emphasize the importance of a comprehensive evaluation framework for CAD-oriented LLMs. Establishing rigorous evaluation methodologies is vital to assess and improve model performance, ensuring robust, reliable, and practical solutions for CAD applications.
## 📚 BlendNet
### 📖 Overview
The dataset contains $12k$ samples. To balance cost savings with data quality and scale, we manually annotated $2k$ samples and used **GPT-4o** to annotate the remaining $10k$ samples.
To ensure diversity, we categorized objects into 16 types, classified instructions into 8 tones, and varied the lengths of the instructions. The figure below illustrate the diversity distribution.
<div align=center>
<img src="assets/training_eval_data.png" width = "640" alt="Diversity" align=center/>
</div>
The figure below illustrates the complexity of tasks in the dataset, demonstrating task difficulty using the metrics—**Unit Number*Excerpt of 12,990 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:041b326c03c42600, topic:large-language-models