Contrastive Language-Image Pretraining
Dépôts
Dépôts de mgrankin
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
MM'21 Main-Track paper
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
A character tokenizer for HuggingFace Transformers
Unsupervised Real Image Super-Resolution via Variational AutoEncoder
This repository contains implementations and illustrative code to accompany DeepMind publications
Entropy Based Sampling and Parallel CoT Decoding
TabNet for fastai
Google Research
Code for the paper "Language Models are Unsupervised Multitask Learners"
Train GPT model helped by CLIP
Multilingual Generative Pretrained Model
minGPT in JAX
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
nanoGPT with octonions
Over9000 optimizer