Llama Cookbook
An official guide and set of recipes for building with Meta's Llama model family, covering getting started with inference, fine-tuning and retrieval-augmented generation, plus end-to-end use cases across model providers.
Llama Cookbook is Meta's official repository for getting started with inference, fine-tuning and end-to-end use cases built on the Llama model family, covering both Llama's text and vision models.
It is organized into getting-started references for inference, fine-tuning and RAG examples, third-party integration recipes from various Llama providers, and end-to-end use cases spanning multiple application domains, including recipes for the Llama API, WhatsApp integration, long-context processing and research paper analysis with Llama 4 models. A src directory holds the original llama-recipes library code.
The repository was renamed from llama-recipes to llama-cookbook, and its models are distributed under Meta's own Llama license and acceptable use policy rather than a standard open source license.