Hands-On-Large-Language-Models

Why we included this project

This is the official code repository for the O'Reilly book by Jay Alammar and Maarten Grootendorst, and it works better as a course than as a single tool. Each chapter ships as a Jupyter notebook you can run as-is, covering tokenization, embeddings, prompt engineering, semantic search, multimodal models, and fine-tuning both representation and generation models. The notebooks carry Colab badges and the authors suggest running them on a free T4 GPU, so you can follow along without standing up your own infrastructure; a setup folder also reproduces the environment locally if you prefer. Developers and small teams who want to get fluent in LLM workflows will find it a practical way to see how ideas like RAG and fine-tuning actually behave in code. It is a teaching resource, not a deployable service, so treat it as a guided tour rather than something to run in production.