Swin Transformer - PyTorch Implementation of the Swin Transformer architecture. This paper presents a new vision Transformer, called Swin Transformer,

Transformer-PyTorch A PyTorch implementation of the Transformer from the paper Attention is All You Need in both Post-LN (Post-LayerNorm) and Pre-LN (

transformer-pytorch Transformer model implemented with Pytorch Attention is all you need-[Paper] Architecture Self-Attention self_attention.py class

Simple Transformer I've written a series of articles on the transformer architecture and language models on Medium. This repository contains an implem