What it does
This project takes Meta's Llama 2 language model and trains it further on Chinese text, with a larger Chinese vocabulary, so it handles Chinese much better. It offers base models for continuing text and "Alpaca" chat models for questions and conversation.
There are several sizes, plus versions that can read very long texts and versions tuned with human feedback to give more appropriate answers.
The project shares its training scripts and explains how to shrink the models to run on a personal computer with popular tools. The README now points people to a newer third-generation project.
Who it's for
Developers and researchers who want an open Chinese-language AI model to run or adapt.
Can I use it without coding?
Developers only. Model files and scripts for technical users; some popular local AI apps can load them. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- YaRN for extending context length (method used, linked in the README)Research paper · Sept 2023
- Position Interpolation for extending context length (method used, linked in the README)Research paper · Jun 2023