lucidrains

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

DALLE-pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers

lion-pytorch

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

soundstorm-pytorch

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

video-diffusion-pytorch

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

muse-maskgit-pytorch

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

phenaki-pytorch

Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch

meshgpt-pytorch

Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

voicebox-pytorch

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

rotary-embedding-torch

Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

ema-pytorch

A simple way to keep track of an Exponential Moving Average (EMA) version of your pytorch model

enformer-pytorch

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

ring-attention-pytorch

Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

CoLT5-attention

Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch

st-moe-pytorch

Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch

lumiere-pytorch

Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch

soft-moe-pytorch

Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch

recurrent-interface-network-pytorch

Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch

flash-attention-jax

Implementation of Flash Attention in Jax

CALM-pytorch

Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind

quartic-transformer

Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)

genetic-algorithm-pytorch

Toy genetic algorithm in Pytorch

SAC-pytorch

Implementation of Soft Actor Critic and some of its improvements in Pytorch

lucidrains.github.io

flash-attention

Fast and memory-efficient exact attention