A Practical Guide to Building a Seq2Seq Transformer from scratch with PyTorch

/

This jupyter notebook details how to build a sequence-to-sequence (Seq2Seq) model using PyTorch, focusing on the Transformer architecture. Our goal is to develop a transpiler that translates and transpiles PL/I code into Kotlin. Throughout the notebook, we’ll cover everything from setting up the necessary libraries to training the model and evaluating its performance