datawhalechina/llms-from-scratch-cn

# Technical Summary Provides hands-on implementation of LLM core components using PyTorch, covering tokenization, attention mechanisms, and GPT-style architectures through progressive Jupyter notebooks alongside detailed theoretical explanations. Includes architecture dissections and implementation guides for multiple production models (ChatGLM3/4, Llama3, RWKV V2-V6, MiniCPM), enabling learners to understand both foundational transformer mechanics and variant design choices across different model families.

4,010 stars. No commits in the last 6 months.