# hyunwoongko/transformer

Transformer: PyTorch Implementation of "Attention Is All You Need"

Repository: https://github.com/hyunwoongko/transformer
Canonical: https://ross.abutalabs.com/products/transformer
Language: Python
License Family: other
Topics: pytorch, transformer, attention, dataset
Last push: 2025-07-15T06:19:46+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 31, release rhythm 35, longevity 100
- inputs: {"age_days": 2514, "days_push": 414, "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 4645, forks 642 (observed 2026-08-28T04:08:55.554891+00:00)

## What it is
A from-scratch PyTorch implementation of the Transformer model from the paper 'Attention Is All You Need', written for educational purposes. It includes readable implementations of positional encoding, multi-head attention, and other core Transformer components.

## Use cases
- learn how the transformer architecture works internally
- understand multi-head attention with code
- study positional encoding implementation in pytorch
- reference implementation of attention is all you need
- teach transformer concepts with a minimal codebase

## When to choose
- you want to read a simple, annotated implementation of the Transformer to learn the architecture
- you need a small educational codebase rather than a production library

## When to avoid
- you need a production-grade, well-tested Transformer implementation (use Hugging Face Transformers or PyTorch's built-in nn.Transformer)
- you need ongoing maintenance or bug-free guarantees - the author explicitly warns the code is not well maintained

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning
- domain: deep-learning, tutorials
- platform: python
- tags: transformer, attention, pytorch-implementation, educational, attention-is-all-you-need, natural-language-processing

## Member repositories
- hyunwoongko/transformer (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:55.554891+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 2026-08-29T18:19:32.208846+00:00, confidence not recorded.
  - readme: https://github.com/hyunwoongko/transformer (fetched 2026-08-28T04:08:55.554891+00:00, sha e4ea53165770)
- Data as of 2026-08-30T08:39:29.467469+00:00.