# huggingface/cookbook

Open-source AI cookbook

Repository: https://github.com/huggingface/cookbook
Canonical: https://ross.abutalabs.com/products/huggingface-cookbook
Homepage: https://huggingface.co/learn/cookbook
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2026-08-25T13:18:33+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 72
- inputs: {"age_days": 1013, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2711, forks 414 (observed 2026-08-28T04:07:11.863668+00:00)

## What it is
A community-driven collection of Jupyter notebooks from Hugging Face demonstrating practical AI application building with open-source tools and models. It covers tasks like fine-tuning, RAG, agents, and inference, published as part of Hugging Face's learn documentation.

## Use cases
- learn how to fine-tune LLMs with TRL and GRPO
- build a RAG pipeline with open-source models
- create AI agents with Hugging Face tools
- find practical notebook examples for machine learning tasks
- post-train a vision-language model for reasoning
- fine-tune LLMs for function calling
- optimize language models with DSPy

## When to choose
- you want hands-on, executable notebook examples using open-source models
- you are learning Hugging Face ecosystem tools like Transformers, TRL, and PEFT
- you need practical recipes for LLM fine-tuning, agents, or RAG
- you prefer community-driven, permissively licensed educational content

## When to avoid
- you need production-ready software or a maintained library rather than tutorials
- you want a structured course with assessments instead of standalone notebooks
- you need vendor-neutral content independent of the Hugging Face ecosystem

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, llm-inference, llm-training, rag, agent-framework, developer-tools
- domain: machine-learning, large-language-models, artificial-intelligence, tutorials, deep-learning
- platform: python, cross-platform
- tags: jupyter-notebooks, cookbook, hugging-face, open-source-models, examples, fine-tuning, ai-agents

## Member repositories
- huggingface/cookbook (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.863668+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 2026-08-30T02:15:34.595894+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/cookbook (fetched 2026-08-28T04:07:11.863668+00:00, sha d67459971e1c)
  - homepage: https://huggingface.co/learn/cookbook (fetched 2026-08-29T09:58:39.439170+00:00, sha beb6ec27c088)
  - site_page: https://huggingface.co/docs (fetched 2026-08-29T09:58:39.441779+00:00, sha bdec26667b98)
  - site_page: https://huggingface.co/pricing (fetched 2026-08-29T09:58:39.444857+00:00, sha de6b7a178be5)
- Data as of 2026-08-30T08:39:29.467469+00:00.