# rasbt/LLM-workshop-2024

A 4-hour coding workshop to understand how LLMs are implemented and used

Repository: https://github.com/rasbt/LLM-workshop-2024
Canonical: https://ross.abutalabs.com/products/llm-workshop-2024
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: large-language-models, llm, pytorch
Last push: 2025-01-13T01:12:23+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 1, release rhythm 35, longevity 57
- inputs: {"age_days": 799, "days_push": 598, "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 1113, forks 384 (observed 2026-08-28T04:03:38.090484+00:00)

## What it is
A 4-hour hands-on coding workshop by Sebastian Raschka that teaches how large language models are implemented and used, based on his 'Build a Large Language Model From Scratch' book. It walks through coding a GPT-like LLM in PyTorch, including the data pipeline, architecture, pretraining, and finetuning with open-source libraries like LitGPT.

## Use cases
- learn how LLMs work by coding one from scratch
- implement a GPT-like model in PyTorch
- understand LLM pretraining and finetuning
- hands-on workshop material for teaching LLM internals
- practice building text tokenization and data pipelines for LLMs
- load pretrained weights and finetune open-source LLMs

## When to choose
- you want a guided, code-first introduction to LLM internals
- you prefer learning by implementing rather than using high-level APIs
- you need structured workshop or course material on pretraining and finetuning
- you want to complement the 'Build an LLM from Scratch' book with runnable notebooks

## When to avoid
- you need a production-ready LLM training framework rather than educational code
- you want to deploy or serve LLMs in applications
- you are looking for a maintained library with API stability guarantees
- you need state-of-the-art training efficiency or distributed training at scale

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, llm-training, deep-learning
- domain: large-language-models, deep-learning, tutorials, education
- platform: python
- tags: llm, pytorch, workshop, gpt, finetuning, pretraining, jupyter-notebooks, educational, gpu

## Member repositories
- rasbt/LLM-workshop-2024 (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.090484+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 2026-08-30T06:42:37.692693+00:00, confidence not recorded.
  - readme: https://github.com/rasbt/LLM-workshop-2024 (fetched 2026-08-28T04:03:38.090484+00:00, sha ae736a29d080)
- Data as of 2026-08-30T08:39:29.467469+00:00.