Pinned Repositories
fast_tabnet
TabNet for fastai
gpt-c
Train GPT model helped by CLIP
mesh-transformer-jax-clip
A fork of kingoflolz/mesh-transformer-jax to train GPT with CLIP supervision
minGPT
minGPT in JAX
over9000
Over9000 optimizer
poetry
ru-gpts
Russian GPT2 models.
ru_transformers
SimpleSelfAttention
mgrankin's Repositories
mgrankin/ru_transformers
mgrankin/over9000
Over9000 optimizer
mgrankin/fast_tabnet
TabNet for fastai
mgrankin/minGPT
minGPT in JAX
mgrankin/ru-gpts
Russian GPT2 models.
mgrankin/mesh-transformer-jax-clip
A fork of kingoflolz/mesh-transformer-jax to train GPT with CLIP supervision
mgrankin/gpt-c
Train GPT model helped by CLIP
mgrankin/poetry
mgrankin/barlowtwins
PyTorch implementation of Barlow Twins.
mgrankin/CLIP_JAX
Contrastive Language-Image Pretraining
mgrankin/clipgan
mgrankin/ContrastiveDecoding
contrastive decoding
mgrankin/deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications
mgrankin/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
mgrankin/dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
mgrankin/dSRVAE
Unsupervised Real Image Super-Resolution via Variational AutoEncoder
mgrankin/FoodSeg103-Benchmark-v1
MM'21 Main-Track paper
mgrankin/google-research
Google Research
mgrankin/gpt-neo
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
mgrankin/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
mgrankin/minGPT-quantize
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
mgrankin/porfirevich
mgrankin/pytorch-vq-vae
PyTorch implementation of VQ-VAE by Aäron van den Oord et al.
mgrankin/RETRO-pytorch
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
mgrankin/rigl
End-to-end training of sparse deep neural networks with little-to-no performance loss.
mgrankin/stihbot
telegram bot for Russian gpt models
mgrankin/tab-transformer-pytorch
Implementation of TabTransformer, attention network for tabular data, in Pytorch
mgrankin/The-Pile
mgrankin/vector-quantize-pytorch
Vector Quantization, in Pytorch
mgrankin/yarn
YaRN: Efficient Context Window Extension of Large Language Models