Foundations-of-LLMs

Why we included this project

If you want to understand how large language models work under the hood rather than just treat them as a black-box API, this book from Zhejiang University is worth a look. It covers the field in six chapters, moving from statistical and Transformer-based language models through the evolution of LLM architectures, prompt engineering, parameter-efficient fine-tuning, model editing, and retrieval-augmented generation. Each chapter comes with a curated list of papers, so you can follow the research behind each technique. The book is updated monthly and is available as a full PDF plus per-chapter files, which makes it easy to use for self-study, as course reading, or to bring new engineers up to speed on an LLM team. It's a learning resource, not runnable software, but for teams that want a solid conceptual foundation before building, it's a handy reference to keep around.