# mlabonne/llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Repository: https://github.com/mlabonne/llm-course
Canonical: https://ross.abutalabs.com/products/llm-course
Homepage: https://mlabonne.github.io/blog/
License: Apache-2.0
License Family: permissive
Topics: course, llm, machine-learning, roadmap, large-language-models
Last push: 2026-02-05T13:09:26+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 66, release rhythm 35, longevity 83
- inputs: {"age_days": 1173, "days_push": 209, "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 82008, forks 9541 (observed 2026-08-28T04:12:21.952337+00:00)

## What it is
A free, structured course for learning about Large Language Models, organized into three parts: LLM Fundamentals, LLM Scientist, and LLM Engineer. It includes roadmaps and hands-on Google Colab notebooks covering fine-tuning, model merging, quantization, evaluation, and deployment.

## Use cases
- learn how large language models work from scratch
- roadmap to become an LLM engineer
- fine-tune LLMs with notebooks
- quantize models to GGUF or GPTQ formats
- merge models with MergeKit
- deploy LLM-based applications
- learn LLM fundamentals like math and neural networks

## When to choose
- you want a free, structured learning path into LLMs
- you prefer hands-on Colab notebooks over theory-only material
- you want coverage of both building (scientist) and deploying (engineer) LLMs

## When to avoid
- you need production-grade tooling rather than educational material
- you want a formal course with certification or instructor support
- you need a maintained software library or framework

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-training, llm-inference, machine-learning, developer-tools
- domain: large-language-models, machine-learning, artificial-intelligence, tutorials, education
- platform: python, cross-platform
- tags: llm-course, roadmap, colab-notebooks, fine-tuning, quantization, model-merging, free-course, web-server

## Member repositories
- mlabonne/llm-course (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:21.952337+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 2026-08-29T16:13:55.880661+00:00, confidence not recorded.
  - readme: https://github.com/mlabonne/llm-course (fetched 2026-08-28T04:12:21.952337+00:00, sha a782c84d7ee6)
  - homepage: https://mlabonne.github.io/blog/ (fetched 2026-08-28T17:40:43.622789+00:00, sha 9cafb46c2bc0)
- Data as of 2026-08-30T08:39:29.467469+00:00.