# KellerJordan/modded-nanogpt

NanoGPT (124M) in 90 seconds

Repository: https://github.com/KellerJordan/modded-nanogpt
Canonical: https://ross.abutalabs.com/products/modded-nanogpt
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-09T22:42:15+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 35, longevity 58
- inputs: {"age_days": 823, "days_push": 24, "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 5707, forks 869 (observed 2026-08-28T04:09:28.132095+00:00)

## What it is
A collaborative speedrun project that trains a GPT-2 (124M) scale language model to 3.28 validation loss on FineWeb in under 75 seconds on 8xH100 GPUs. It serves as both a record-setting training implementation and a learning resource showcasing modern LLM training techniques like the Muon optimizer, FP8, and architectural modernizations.

## Use cases
- learn how to train a GPT-2 scale language model efficiently
- study modern LLM training optimizations like Muon and FP8
- benchmark GPU training speed for small language models
- find the fastest algorithm to train a 124M parameter transformer
- reproduce a fast GPT-2 replication on H100 GPUs
- learn modern transformer architecture tricks like QK-Norm and rotary embeddings

## When to choose
- you want to learn state-of-the-art techniques for training small language models quickly
- you have access to 8xH100 GPUs and want to reproduce or compete in the speedrun
- you want a reference implementation of the Muon optimizer and modern GPT training tricks

## When to avoid
- you need a production training framework with configuration, checkpointing, and multi-dataset support
- you lack high-end NVIDIA GPUs, since the code is heavily tuned for 8xH100 setups
- you want to train large models or fine-tune existing ones rather than a fixed 124M GPT-2 scale target

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-training, benchmarking, machine-learning
- domain: deep-learning, large-language-models, gpu-computing, tutorials
- platform: python
- tags: nanogpt, speedrun, muon-optimizer, h100, training-efficiency, pytorch, fineweb, gpu, linux

## Member repositories
- KellerJordan/modded-nanogpt (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.132095+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 2026-08-29T17:53:32.730015+00:00, confidence not recorded.
  - readme: https://github.com/KellerJordan/modded-nanogpt (fetched 2026-08-28T04:09:28.132095+00:00, sha 06472d0cc761)
- Data as of 2026-08-30T08:39:29.467469+00:00.