jadore801120/attention-is-all-you-need-pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

9784 stars · 2096 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch implementation of the Transformer model from the paper 'Attention Is All You Need', including training and translation scripts for sequence-to-sequence tasks. It serves as a reference implementation for learning how self-attention-based models work.

Use cases

• implement the transformer model from scratch in pytorch
• learn how self-attention works
• train a sequence-to-sequence translation model
• study the attention is all you need paper with code
• reproduce the wmt 2014 english-to-german translation results

When to choose

• you want a readable, minimal reference implementation of the original Transformer architecture
• you are learning deep learning and want to study self-attention code
• you need a starting point for seq2seq translation experiments in PyTorch

When to avoid

• you need a production-grade, well-maintained transformer library
• you want optimized inference or the latest model variants
• you need BPE-based training pipelines, which are incomplete and untested

Facets

library · maturity maintenance

machine-learning deep-learning nlp deep-learning machine-learning python transformer self-attention sequence-to-sequence machine-translation pytorch research-code attention-mechanism natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jadore801120/attention-is-all-you-need-pytorch")