# fastai/lm-hackers

Hackers' Guide to Language Models

Repository: https://github.com/fastai/lm-hackers
Canonical: https://ross.abutalabs.com/products/lm-hackers
Homepage: https://fastai.github.io/lm-hackers/lm-hackers.html
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2024-12-13T07:28:13+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 76
- inputs: {"age_days": 1074, "days_push": 628, "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 1869, forks 310 (observed 2026-08-28T04:05:46.610148+00:00)

## What it is
A Jupyter notebook and accompanying video guide from fast.ai explaining how language models work, including tokenization, base models, instruction tuning, and RLHF. It also includes configuration files for fine-tuning models with axolotl.

## Use cases
- learn how large language models work from scratch
- understand tokenization and how LLMs process text
- get started with fine-tuning open source LLMs using axolotl
- learn to build applications on top of OpenAI language model APIs
- understand instruction tuning and RLHF concepts
- follow a hands-on hacker-style introduction to language models

## When to choose
- you want a fast, practical video-plus-notebook introduction to LLMs
- you are a developer learning to use and fine-tune language models
- you want example axolotl configs for fine-tuning

## When to avoid
- you need production-ready LLM inference or training code
- you want a comprehensive structured course rather than a single notebook
- you need up-to-date coverage of the newest LLM techniques

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-inference, llm-training, prompt-engineering, rag
- domain: large-language-models, tutorials, artificial-intelligence, education
- platform: python, cli
- tags: jupyter-notebook, tutorial, fine-tuning, axolotl, openai, video-course

## Member repositories
- fastai/lm-hackers (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:46.610148+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 2026-08-30T03:15:12.035090+00:00, confidence not recorded.
  - readme: https://github.com/fastai/lm-hackers (fetched 2026-08-28T04:05:46.610148+00:00, sha c56415809ca8)
  - homepage: https://fastai.github.io/lm-hackers/lm-hackers.html (fetched 2026-08-29T10:54:14.265806+00:00, sha 1a5abcbcccfc)
- Data as of 2026-08-30T08:39:29.467469+00:00.