# meta-llama/llama-cookbook

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

Repository: https://github.com/meta-llama/llama-cookbook
Canonical: https://ross.abutalabs.com/products/llama-cookbook
Homepage: https://www.llama.com
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: ai, finetuning, langchain, llama, llama2, llm, machine-learning, python, pytorch, vllm
Last push: 2026-05-19T18:42:31+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 28, longevity 81
- inputs: {"age_days": 1143, "days_push": 106, "days_rel": 588, "gap_med": 59.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18558, forks 2765 (observed 2026-08-28T04:11:26.794894+00:00)

## What it is
Meta's official collection of Jupyter notebook recipes and guides for building with the Llama model family, covering inference, fine-tuning, RAG, and end-to-end use cases. It includes integrations with third-party providers and the Llama API.

## Use cases
- learn how to run inference with Llama models
- fine-tune Llama for domain adaptation
- build a RAG pipeline with Llama
- build a WhatsApp bot with Llama 4
- analyze research papers with LLMs
- get started with the Llama API
- run long-context workloads with Llama 4 Scout

## When to choose
- you want official, maintained examples for the Llama model family
- you need end-to-end recipes combining inference, fine-tuning, and RAG
- you want provider-specific integration guides (vLLM, LangChain, cloud services)

## When to avoid
- you need a production library rather than example notebooks
- you work with non-Llama models exclusively
- you need a framework with stable APIs to build applications on

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, llm-training, rag, prompt-engineering, agent-framework
- domain: large-language-models, artificial-intelligence, tutorials, machine-learning
- platform: python, cross-platform
- tags: llama, fine-tuning, jupyter-notebooks, recipes, vllm, langchain, meta

## Member repositories
- meta-llama/llama-cookbook (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.794894+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:02:01.067447+00:00, confidence not recorded.
  - readme: https://github.com/meta-llama/llama-cookbook (fetched 2026-08-28T04:11:26.794894+00:00, sha 3b7d2eddb4e4)
  - homepage: https://www.llama.com (fetched 2026-08-29T07:59:34.137773+00:00, sha b51dbbb6c49b)
  - registry_pypi: https://pypi.org/pypi/llama-cookbook/json (fetched 2026-08-29T07:59:34.147209+00:00, sha ad1284a37e4d)
- Data as of 2026-08-30T08:39:29.467469+00:00.