Implementation of the Transformer architecture described by Vaswani et al. in "Attention Is All You Need"
MIT License
Implementation of the Transformer architecture described by Vaswani et al. in "Attention Is All You Need" using the Keras Utility & Layer Collection (kulc).
This repository contains the code the create the model, train and evaluate it. Furthermore, it contains utility code to load a translation dataset (en2de
) to run the experiments on it.