# karpathy/ng-video-lecture

Repository: https://github.com/karpathy/ng-video-lecture
Canonical: https://ross.abutalabs.com/products/ng-video-lecture
Language: Python
License Family: other
Last push: 2024-01-31T13:43:36+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 94
- inputs: {"age_days": 1324, "days_push": 945, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4937, forks 1352 (observed 2026-08-28T04:09:02.725951+00:00)

## What it is
The companion code repository for Andrej Karpathy's 'Neural Networks: Zero To Hero' video lecture on building a GPT model from scratch (nanoGPT). It is meant for learners to follow along, hack on, and walk through the git history of a minimal GPT implementation.

## Use cases
- learn how a GPT transformer is implemented from scratch
- follow along with a video lecture on building nanoGPT
- study the git history of a minimal GPT codebase
- hack on a small educational GPT implementation
- understand transformer training basics in Python

## When to choose
- you want educational, minimal GPT code tied to a lecture
- you prefer learning by reading and modifying a small codebase

## When to avoid
- you need a production-ready or well-optimized GPT implementation
- you need model initialization best practices not covered in this code
- you need a maintained library with a license file and releases

## Facets
- artifact type: learning-resource
- maturity: stable
- function: machine-learning, deep-learning, llm-training
- domain: deep-learning, large-language-models, tutorials, education
- platform: python
- tags: gpt, transformer, nanogpt, educational-code, video-lecture, pytorch

## Member repositories
- karpathy/ng-video-lecture (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:02.725951+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 2026-08-29T18:17:56.875213+00:00, confidence not recorded.
  - readme: https://github.com/karpathy/ng-video-lecture (fetched 2026-08-28T04:09:02.725951+00:00, sha 427c41751495)
- Data as of 2026-08-30T08:39:29.467469+00:00.