rosinality

stylegan2-pytorch

Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

vq-vae-2-pytorch

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch

style-based-gan-pytorch

Implementation A Style-Based Generator Architecture for Generative Adversarial Networks in PyTorch

alias-free-gan-pytorch

Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch

glow-pytorch

PyTorch implementation of Glow

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Models in PyTorch

ml-papers

My collection of machine learning papers

swapping-autoencoder-pytorch

Unofficial implementation of Swapping Autoencoder for Deep Image Manipulation (https://arxiv.org/abs/2007.00653) in PyTorch

vision-transformers-pytorch

Implementation of various Vision Transformers I found interesting

nerf-pytorch

tensorfn

Weakly opinionated library for implementing ML models. Less boilerplate, More rigor

instant-ngp-pytorch

Study for Instant neural graphics primitives (Unofficial)

meshfn

Framework for Human Alignment Learning

nansy-pytorch

Unofficial implementation of Neural Analysis and Synthesis

arxiv-sanity

arXiv feed tool that heavily inspired by Arxiv Sanity Preserver

dockerfiles

dockerfiles

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

langfn

A DSL for LLMs

rosinality.github.io

semantic-segmentation

Nvidia Semantic Segmentation monorepo

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

flaxformer

halite

Acceleration framework for Human Alignment Learning

jujutsu-tutorial

lm-exp

OpenMoE

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

seqio

Task-based datasets, preprocessing, and evaluation for sequence models.

slickconf

Configuration library for machine learning projects

t5x