gordicaleksa/pytorch-original-transformer

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

50
/ 100
Established

This project offers a foundational implementation of the original Transformer model for individuals eager to learn about its inner workings. It takes text data, specifically English and German sentences, and translates them, producing translated text. It's designed for machine learning students, researchers, or practitioners who want to understand the core concepts behind modern language models.

1,085 stars. No commits in the last 6 months.

Use this if you are studying neural machine translation and want to explore the Transformer architecture with practical examples and visualizations.

Not ideal if you need a production-ready, state-of-the-art machine translation system or a library for high-performance NLP applications.

neural-machine-translation natural-language-processing language-modeling deep-learning-education text-translation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,085

Forks

188

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 27, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/gordicaleksa/pytorch-original-transformer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.