meta-llama/llama-cookbook

Project overview

Official tutorials and reference recipes for building applications with Llama Text and Vision models. Covers inference, fine-tuning, and retrieval-augmented generation (RAG) through runnable Python code and Jupyter notebooks.

Use cases

Learning & Education

Deployment

Refer to project documentation

License

MIT

Best for

• Developers and AI engineers who need official, code-based tutorial references for building applications with Llama models.
• Users looking for structured examples for fine-tuning, inferencing, or implementing retrieval-augmented generation.

Key capabilities

• Includes reference examples and frequently asked questions for fine-tuning Llama models.
• Provides reference examples for executing model inferencing tasks.
• Contains reference examples for implementing Retrieval-Augmented Generation.

Limitations and risks

• Following a recent refactor, some links may be broken or folders missing; users are directed to an archive branch for previous content.

Getting started

• Setup difficulty is medium and requires users to run Jupyter notebooks and Python source code to execute the provided examples.

Evidence and sources

• README: Welcome to the official repository for helping you get started with inference, fine-tuning and end-to-end use-cases of building with the Llama Model family.
• README: This repository covers the most popular community approaches, use-cases and the latest recipes for Llama Text and Vision models.
• README: - [Getting Started](https://github.com/meta-llama/llama-cookbook/tree/main/getting-started/): Reference for inferencing, fine-tuning and RAG examples - [src](https://github.com/me…
• README: **Q:** Some links are broken/folders are missing: **A:** We recently did a refactor of the repo, archive-main is a snapshot branch from before the refactor.
• Release: Llama-cookbook v0.0.5 Release

Reviewed at: 2026-07-17T12:24:56Z