SamLynnEvans/Transformer

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1430 stars · 346 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of the Transformer seq2seq model designed to build language translators from parallel corpora. It accompanies a tutorial explaining how to code the Transformer architecture from scratch.

Use cases

• train a language translator from parallel text files
• learn how the transformer model is implemented in pytorch
• build a machine translation model for supported spacy languages
• experiment with transformer hyperparameters like layers and attention heads
• reproduce a seq2seq translation model on a single gpu

When to choose

• you want a readable, educational transformer implementation for translation
• you have parallel sentence pairs in languages supported by spacy
• you want to train a small seq2seq model on a single consumer gpu

When to avoid

• you need production-grade translation with subword tokenization and many languages
• you want a maintained library with active development and broad model support
• you need pretrained multilingual models rather than training from scratch

Facets

library · maturity maintenance

machine-learning deep-learning nlp llm-training machine-learning deep-learning python cross-platform transformer seq2seq pytorch machine-translation educational natural-language-processing gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="SamLynnEvans/Transformer")