What it does
Happy-LLM is a free, step-by-step course on large language models (LLMs), the technology behind chatbots like ChatGPT. It starts from the basics of how computers handle language and builds up to how today's big models are designed and trained.
Chapters cover the Transformer design that most modern AI models use, how models are pre-trained and fine-tuned, and how to build a small model similar to LLaMA2 yourself. Later chapters look at uses like RAG (looking things up in documents) and AI agents.
The course is written in Chinese and can be read online. Small models trained in the course are available to download.
Who it's for
Students and self-learners who read Chinese and want a deep understanding of how AI language models work.
Can I use it without coding?
Yes. You can read it free online; the hands-on chapters need Python programming. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Web browser
- Computer
- An ordinary computer is fine
- API key
- Not needed
Try it
- Follow the chapters in order, from language basics to building a small model.
- Check the learning and environment guide before running any of the code.
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.
- No standard license listed. Check the GitHub page before using it for business.
- More on staying safe