# HandsOnLLM/Hands-On-Large-Language-Models

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Repository: https://github.com/HandsOnLLM/Hands-On-Large-Language-Models
Canonical: https://ross.abutalabs.com/products/hands-on-large-language-models
Homepage: https://www.llm-book.com/
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: artificial-intelligence, book, large-language-models, llm, llms, oreilly, oreilly-books
Last push: 2026-04-24T10:20:08+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 35, longevity 56
- inputs: {"age_days": 796, "days_push": 131, "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 28623, forks 6570 (observed 2026-08-28T04:11:52.734979+00:00)

## What it is
The official companion code repository for the O'Reilly book 'Hands-On Large Language Models' by Jay Alammar and Maarten Grootendorst, containing Jupyter notebook examples for all chapters. It is a visually-driven educational resource with nearly 300 custom figures covering LLM concepts, tokenizers, semantic search, and RAG.

## Use cases
- learn how large language models work with illustrated explanations
- find hands-on jupyter notebook examples for LLM techniques
- understand tokenizers, embeddings, and semantic search
- learn to build RAG applications step by step
- study transformer architecture with visual diagrams
- get a practical introduction to using open-source LLMs

## When to choose
- you want a structured, book-style learning path for LLMs
- you prefer visual, illustrated explanations of complex concepts
- you want runnable notebook code accompanying each topic
- you are a beginner-to-intermediate practitioner entering the LLM field

## When to avoid
- you need production-ready LLM application code or a library
- you want a comprehensive reference for training LLMs from scratch at scale
- you are looking for a tool or framework rather than educational material

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, llm-inference, rag, nlp, data-science
- domain: large-language-models, artificial-intelligence, machine-learning, tutorials
- platform: python, cross-platform
- tags: book, jupyter-notebooks, oreilly, educational, illustrated-guide, transformers, semantic-search, embeddings, natural-language-processing

## Member repositories
- HandsOnLLM/Hands-On-Large-Language-Models (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:52.734979+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 2026-08-29T16:54:21.000633+00:00, confidence not recorded.
  - readme: https://github.com/HandsOnLLM/Hands-On-Large-Language-Models (fetched 2026-08-28T04:11:52.734979+00:00, sha b13a601331f3)
  - homepage: https://www.llm-book.com/ (fetched 2026-08-29T07:50:40.988391+00:00, sha b6ed10a443ab)
- Data as of 2026-08-30T08:39:29.467469+00:00.