#57 · Primary category： Foundation Models
ChatLaw
ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型
Project last updated：01/04/25
GitHub Stars
7.6K
Forks
618
Contributors
6
License
AGPL-3.0
Why we included this project
Chinese legal work needs language precision that general English-focused models rarely deliver, and ChatLaw is built around that gap. The project ships a family of models, from a 4x7B Mixture-of-Experts variant on InternLM to a text-similarity model trained on 93,000 court rulings, so queries get matched to the right statutes and case law instead of generic answers. Its paper reports better results than GPT-4 on Chinese legal benchmarks like Lawbench, which matters when responses have to rest on real legal reasoning. The multi-agent setup, modeled on law firm workflows, also cuts down on hallucinations. Teams building legal assistants, contract review, or compliance tools for Chinese users get checkpoints they can fine-tune or serve, plus a documented training approach worth studying.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities