What it does
MiniMind is an educational project for training a very small language model, the technology behind chatbots, completely from scratch. Its makers say a basic training run takes about two hours on one consumer graphics card.
It covers every stage: preparing data, initial training, fine-tuning to follow instructions, and more advanced steps such as learning from feedback and using tools. The core code is written from the ground up so you can read how each part works, rather than hiding it inside big libraries.
It also includes training data, finished small models, a simple chat web page and a server that other chat apps can connect to. The main README is in Chinese, with an English version available.
Who it's for
Students and developers who want to understand how language models are built by doing it themselves.
Can I use it without coding?
Developers only. Needs Python, some machine-learning knowledge and a graphics card. There is an online demo for just trying the model. 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