#3333rd of 33 in Learning and cookbooks
llama-cookbook
Official Meta notebooks for running, fine-tuning and building apps with Llama models
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 18.6k
- License
- MIT
- Last commit
- Nov 2025
- Last release
- Jan 2025
- Language
- Jupyter Notebook
Missed the latest GitHub check; these facts may be older.
Overview
Meta's cookbook of Jupyter notebooks and scripts covering Llama inference, fine-tuning, RAG and end-to-end use cases, such as a WhatsApp bot on Llama API, research paper analysis and book character mind maps. It also holds third-party provider recipes and the source of the original llama-recipes fine-tuning library. Recipes target Llama 4 text and vision models, with older Llama versions covered too.
Who it is for: Engineers learning to run, fine-tune and build apps with Llama models
Strengths
- Maintained by Meta, with recipes for Llama 4 Scout and Maverick
- Covers inference, fine-tuning, RAG and end-to-end apps in one repository
- Includes third-party provider integrations and a fine-tuning FAQ
- MIT-licensed code
Weaknesses
- Llama-specific; recipes do not target other model families
- Model weights fall under separate Meta Llama licenses and use policies
- Last tagged release is January 2025; repo refactor broke some old links
- Notebook format; no installable app or service
What it needs
- Needs Jupyter, Llama API (some recipes), Hugging Face
- Models: Llama 4, Llama 3.3, Llama 3.2, Llama 3.1, Llama 3
Also in Learning and cookbooks
See all 33| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 87 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | hello-agentsChinese-language course on building LLM agents from scratch | 78 out of 100 |
| #4 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 77 out of 100 |
| #5 | ai-agent-bookOpen book on AI agent design, with 109 runnable companion experiments | 77 out of 100 |