Phil Wang (@lucidrains)
github

lucidrains

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    127,739
  • Global Rank 28 (Top 0.01 %)
  • Followers 31,737
  • Registered over 15 years ago
  • Most used languages
    Python
         96.2 %
    Nim
         1.3 %
    Others     2.5 %
  • Location πŸ‡ΊπŸ‡Έ United States
  • Country Total Rank 39
  • Country Ranking
    Python
         6
    Cuda     27
    Nim
         59
    Crystal
         185
    HTML
         1,058
    CoffeeScript
         2,370

Top repositories

1

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Python
13,633
star
2

DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
Python
11,068
star
3

imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
Python
7,832
star
4

PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Python
7,611
star
5

DALLE-pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Python
5,132
star
6

deep-daze

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
Python
4,387
star
7

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Python
3,959
star
8

stylegan2-pytorch

Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Python
3,433
star
9

musiclm-pytorch

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch
Python
3,048
star
10

x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers
Python
2,707
star
11

big-sleep

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun
Python
2,446
star
12

audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
Python
2,285
star
13

lion-pytorch

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
Python
1,933
star
14

toolformer-pytorch

Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
Python
1,905
star
15

reformer-pytorch

Reformer, the efficient Transformer, in Pytorch
Python
1,870
star
16

make-a-video-pytorch

Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
Python
1,853
star
17

gigagan-pytorch

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
Python
1,632
star
18

alphafold2

To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released
Python
1,536
star
19

lightweight-gan

Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two
Python
1,526
star
20

lambda-networks

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute
Python
1,516
star
21

byol-pytorch

Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
Python
1,497
star
22

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
Python
1,253
star
23

naturalspeech2-pytorch

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
Python
1,214
star
24

flamingo-pytorch

Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch
Python
1,155
star
25

video-diffusion-pytorch

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch
Python
1,141
star
26

soundstorm-pytorch

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
Python
1,130
star
27

CoCa-pytorch

Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch
Python
990
star
28

performer-pytorch

An implementation of Performer, a linear attention-based transformer, in Pytorch
Python
937
star
29

perceiver-pytorch

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch
Python
935
star
30

RETRO-pytorch

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
Python
835
star
31

mlp-mixer-pytorch

An All-MLP solution for Vision, from Google AI
Python
833
star
32

muse-maskgit-pytorch

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch
Python
821
star
33

PaLM-pytorch

Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways
Python
812
star
34

vector-quantize-pytorch

Vector Quantization, in Pytorch
Python
810
star
35

phenaki-pytorch

Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch
Python
724
star
36

x-clip

A concise but complete implementation of CLIP with various experimental improvements from recent papers
Python
658
star
37

bottleneck-transformer-pytorch

Implementation of Bottleneck Transformer in Pytorch
Python
632
star
38

memorizing-transformers-pytorch

Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
Python
614
star
39

TimeSformer-pytorch

Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
Python
613
star
40

MEGABYTE-pytorch

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
Python
594
star
41

meshgpt-pytorch

Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch
Python
564
star
42

nuwa-pytorch

Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch
Python
531
star
43

voicebox-pytorch

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch
Python
521
star
44

point-transformer-pytorch

Implementation of the Point Transformer layer, in Pytorch
Python
518
star
45

parti-pytorch

Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch
Python
509
star
46

tab-transformer-pytorch

Implementation of TabTransformer, attention network for tabular data, in Pytorch
Python
485
star
47

alphafold3-pytorch

Implementation of Alphafold 3 in Pytorch
Python
483
star
48

linear-attention-transformer

Transformer based on a variant of attention that is linear complexity in respect to sequence length
Python
468
star
49

magvit2-pytorch

Implementation of MagViT2 Tokenizer in Pytorch
Python
436
star
50

ema-pytorch

A simple way to keep track of an Exponential Moving Average (EMA) version of your pytorch model
Python
408
star
51

egnn-pytorch

Implementation of E(n)-Equivariant Graph Neural Networks, in Pytorch
Python
400
star
52

g-mlp-pytorch

Implementation of gMLP, an all-MLP replacement for Transformers, in Pytorch
Python
391
star
53

recurrent-memory-transformer-pytorch

Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch
Python
384
star
54

ring-attention-pytorch

Implementation of πŸ’ Ring Attention, from Liu et al. at Berkeley AI, in Pytorch
Python
380
star
55

siren-pytorch

Pytorch implementation of SIREN - Implicit Neural Representations with Periodic Activation Function
Python
377
star
56

enformer-pytorch

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch
Python
352
star
57

iTransformer

Unofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant group
Python
349
star
58

robotic-transformer-pytorch

Implementation of RT1 (Robotic Transformer) in Pytorch
Python
346
star
59

memory-efficient-attention-pytorch

Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(nΒ²) Memory"
Python
342
star
60

FLASH-pytorch

Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"
Python
334
star
61

bit-diffusion

Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch
Python
313
star
62

medical-chatgpt

Implementation of ChatGPT, but tailored towards primary care medicine, with the reward being able to collect patient histories in a thorough and efficient manner and come up with a reasonable differential diagnosis
Python
311
star
63

slot-attention

Implementation of Slot Attention from GoogleAI
Python
303
star
64

q-transformer

Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind
Python
293
star
65

BS-RoFormer

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
Python
289
star
66

classifier-free-guidance-pytorch

Implementation of Classifier Free Guidance in Pytorch, with emphasis on text conditioning, and flexibility to include multiple text embedding models
Python
282
star
67

transformer-in-transformer

Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch
Python
277
star
68

axial-attention

Implementation of Axial attention - attending to multi-dimensional data efficiently
Python
273
star
69

conformer

Implementation of the convolutional module from the Conformer paper, for use in Transformers
Python
272
star
70

mixture-of-experts

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
Python
264
star
71

deformable-attention

Implementation of Deformable Attention in Pytorch from the paper "Vision Transformer with Deformable Attention"
Python
258
star
72

magic3d-pytorch

Implementation of Magic3D, Text to 3D content synthesis, in Pytorch
Python
258
star
73

x-unet

Implementation of a U-net complete with efficient attention as well as the latest research findings
Python
252
star
74

routing-transformer

Fully featured implementation of Routing Transformer
Python
251
star
75

Adan-pytorch

Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch
Python
245
star
76

spear-tts-pytorch

Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch
Python
241
star
77

st-moe-pytorch

Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch
Python
237
star
78

perfusion-pytorch

Implementation of Key-Locked Rank One Editing, from Nvidia AI
Python
229
star
79

equiformer-pytorch

Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein folding
Python
227
star
80

segformer-pytorch

Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch
Python
227
star
81

sinkhorn-transformer

Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention
Python
222
star
82

pixel-level-contrastive-learning

Implementation of Pixel-level Contrastive Learning, proposed in the paper "Propagate Yourself", in Pytorch
Python
220
star
83

lumiere-pytorch

Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch
Python
216
star
84

local-attention

An implementation of local windowed attention for language modeling
Python
216
star
85

CoLT5-attention

Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch
Python
216
star
86

natural-speech-pytorch

Implementation of the neural network proposed in Natural Speech, a text-to-speech generator that is indistinguishable from human recordings for the first time, from Microsoft Research
Python
215
star
87

soft-moe-pytorch

Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch
Python
211
star
88

se3-transformer-pytorch

Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. This specific repository is geared towards integration with eventual Alphafold2 replication.
Python
211
star
89

block-recurrent-transformer-pytorch

Implementation of Block Recurrent Transformer - Pytorch
Python
205
star
90

Mega-pytorch

Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena
Python
201
star
91

simple-hierarchical-transformer

Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
Python
198
star
92

med-seg-diff-pytorch

Implementation of MedSegDiff in Pytorch - SOTA medical segmentation using DDPM and filtering of features in fourier space
Python
195
star
93

triton-transformer

Implementation of a Transformer, but completely in Triton
Python
195
star
94

jax2torch

Use Jax functions in Pytorch
Python
194
star
95

flash-cosine-sim-attention

Implementation of fused cosine similarity attention in the same style as Flash Attention
Cuda
194
star
96

halonet-pytorch

Implementation of the πŸ˜‡ Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones
Python
193
star
97

attention

This repository will house a visualization that will attempt to convey instant enlightenment of how Attention works to someone not working in artificial intelligence, with 3Blue1Brown as inspiration
HTML
189
star
98

recurrent-interface-network-pytorch

Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch
Python
188
star
99

electra-pytorch

A simple and working implementation of Electra, the fastest way to pretrain language models from scratch, in Pytorch
Python
186
star
100

PaLM-jax

Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)
Python
184
star