Simple implementation of FAVOR attention layer
BSD-3-CLAUSE License
Statistics for this project are still being loaded, please check back later.
An implementation of Performer, a linear attention-based transformer, in Pytorch
Implementation of Nyström Self-attention, from the paper Nyströmformer
Implementation of Flash Attention in Jax
Source code for "On the Relationship between Self-Attention and Convolutional Layers"
Implementation of the Point Transformer layer, in Pytorch
MSA Transformer reproduction code
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attenti...
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
Fast and memory-efficient exact attention
Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizin...
A Pytorch implementation of Attention on Attention module (both self and guided variants), for Vi...
Implementation of Slot Attention from GoogleAI
A simple cross attention that updates both the source and target in one step
Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Paramete...
Pytorch implementation of the reknowned "Attention Is All You Need" paper - NeurIPS 2017