tunz/transformer-pytorch
A PyTorch implementation of the Transformer neural network architecture for sequence-to-sequence tasks like machine translation.
Not currently ranked — collecting fresh signals.
star history
This repository provides a reference implementation of the Transformer model in PyTorch, matching the original “Attention is All You Need” paper architecture. It supports training on standard NLP benchmarks including WMT32k (German-English translation) and lm1b datasets. Users can train the model and use a decoder script to translate sentences with a trained model.
Frequently asked
- What is tunz/transformer-pytorch?
- A PyTorch implementation of the Transformer neural network architecture for sequence-to-sequence tasks like machine translation.
- Is transformer-pytorch open source?
- Yes — tunz/transformer-pytorch is open source, released under the MIT license.
- What language is transformer-pytorch written in?
- tunz/transformer-pytorch is primarily written in Python.
- How popular is transformer-pytorch?
- tunz/transformer-pytorch has 491 stars on GitHub.
- Where can I find transformer-pytorch?
- tunz/transformer-pytorch is on GitHub at https://github.com/tunz/transformer-pytorch.