mgrankin Goto Github PK

barlowtwins

PyTorch implementation of Barlow Twins.

clip_jax

Contrastive Language-Image Pretraining

clipgan

contrastivedecoding

contrastive decoding

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

deepspeed

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

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

dsrvae

Unsupervised Real Image Super-Resolution via Variational AutoEncoder

fast_tabnet

TabNet for fastai

foodseg103-benchmark-v1

MM'21 Main-Track paper

google-research

Google Research

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

gpt-c

Train GPT model helped by CLIP

gpt-neo

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

mesh-transformer-jax-clip

A fork of kingoflolz/mesh-transformer-jax to train GPT with CLIP supervision

mingpt

minGPT in JAX

mingpt-quantize

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

over9000

Over9000 optimizer

poetry

porfirevich

pytorch-vq-vae

PyTorch implementation of VQ-VAE by Aäron van den Oord et al.

retro-pytorch

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

rigl

End-to-end training of sparse deep neural networks with little-to-no performance loss.

ru-gpts

Russian GPT2 models.

ru_transformers

simpleselfattention

stihbot

telegram bot for Russian gpt models

tab-transformer-pytorch

Implementation of TabTransformer, attention network for tabular data, in Pytorch

the-pile