Transformer From Scratch
An implementation of the Transformer from "Attention Is All You Need"
TransformerFromScratch is supposed to be an educational project to learn more about the mechanisms that make Transformers the modern day success that is. The github repo contains my implementation after navigating various resources that have already covered this topic in depth. The code takes inspiration from many of these different sources.
The project can be found on the github repo TransformerFromScratch.
(WORK IN PROGRESS)