#Attention-mechanisms

Showing 50 of 50 repositories tagged #attention-mechanisms, ranked by stars

lucidrains
lucidrains
PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Score
100
★ 7.9k ⑂ 674 +2/day
Python
cmhungsteve
cmhungsteve
Awesome-Transformer-Attention

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

Score
98
★ 5.0k ⑂ 497 +2/day
lucidrains
lucidrains
musiclm-pytorch

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

Score
93
★ 3.3k ⑂ 264 +3/day
Python
lucidrains
lucidrains
audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

Score
91
★ 2.6k ⑂ 279 +2/day
Python
lucidrains
lucidrains
toolformer-pytorch

Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI

Score
82
★ 2.1k ⑂ 132 +1/day
Python
lucidrains
lucidrains
make-a-video-pytorch

Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch

Score
84
★ 2.0k ⑂ 184
Python
lucidrains
lucidrains
alphafold3-pytorch

Implementation of Alphafold 3 from Google Deepmind in Pytorch

Score
95
★ 1.7k ⑂ 226
Python
pprp
pprp
awesome-attention-mechanism-in-cv

Awesome List of Attention Modules and Plug&Play Modules in Computer Vision

Score
75
★ 1.3k ⑂ 172
Python
lucidrains
lucidrains
muse-maskgit-pytorch

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

Score
50
★ 919 ⑂ 86
Python
lucidrains
lucidrains
BS-RoFormer

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

Score
100
★ 868 ⑂ 40 +5/day
Python
lucidrains
lucidrains
meshgpt-pytorch

Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

Score
68
★ 861 ⑂ 67
Python
lucidrains
lucidrains
phenaki-pytorch

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

Score
66
★ 792 ⑂ 81
Python
kyegomez
kyegomez
LongNet

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

Score
0
★ 721 ⑂ 61
Python
lucidrains
lucidrains
magvit2-pytorch

Implementation of MagViT2 Tokenizer in Pytorch

Score
61
★ 667 ⑂ 34
Python
lucidrains
lucidrains
MEGABYTE-pytorch

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

Score
64
★ 655 ⑂ 55
Python
lucidrains
lucidrains
mmdit

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

Score
89
★ 549 ⑂ 16
Python
lucidrains
lucidrains
iTransformer

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

Score
57
★ 537 ⑂ 38
Python
lucidrains
lucidrains
local-attention

An implementation of local windowed attention for language modeling

Score
55
★ 503 ⑂ 49 +1/day
Python
lucidrains
lucidrains
robotic-transformer-pytorch

Implementation of RT1 (Robotic Transformer) in Pytorch

Score
48
★ 454 ⑂ 37 +1/day
Python
landskape-ai
landskape-ai
triplet-attention

Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]

Score
50
★ 442 ⑂ 51
Jupyter Notebook
lucidrains
lucidrains
recurrent-memory-transformer-pytorch

Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch

Score
45
★ 424 ⑂ 19
Python
lucidrains
lucidrains
q-transformer

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

Score
43
★ 407 ⑂ 22
Python
lucidrains
lucidrains
clinical-calculator-tooluse

Explorations into training LLMs to use clinical calculators from patient history, using open sourced models. Will start with Wells' Criteria

Score
52
★ 315 ⑂ 32
Python
lucidrains
lucidrains
equiformer-pytorch

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

Score
41
★ 290 ⑂ 31
Python
cbaziotis
cbaziotis
neat-vision

Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

Score
0
★ 251 ⑂ 24
Vue
lucidrains
lucidrains
CoLT5-attention

Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch

Score
34
★ 230 ⑂ 14
Python
lucidrains
lucidrains
simple-hierarchical-transformer

Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT

Score
77
★ 228 ⑂ 14
Python
lucidrains
lucidrains
flash-attention-jax

Implementation of Flash Attention in Jax

Score
39
★ 228 ⑂ 25
Python
lucidrains
lucidrains
block-recurrent-transformer-pytorch

Implementation of Block Recurrent Transformer - Pytorch

Score
36
★ 226 ⑂ 20
Python
kyegomez
kyegomez
MambaTransformer

Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling

Score
86
★ 225 ⑂ 16
Python
lucidrains
lucidrains
flash-cosine-sim-attention

Implementation of fused cosine similarity attention in the same style as Flash Attention

Score
32
★ 220 ⑂ 12
Cuda
lucidrains
lucidrains
recurrent-interface-network-pytorch

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

Score
80
★ 209 ⑂ 14
Python
lucidrains
lucidrains
Mega-pytorch

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

Score
30
★ 207 ⑂ 11
Python
lucidrains
lucidrains
coconut-pytorch

Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch

Score
27
★ 183 ⑂ 8
Python
lucidrains
lucidrains
CALM-pytorch

Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind

Score
25
★ 177 ⑂ 9
Python
jshuadvd
jshuadvd
LongRoPE

Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper

Score
23
★ 154 ⑂ 13 +1/day
Python
lucidrains
lucidrains
locoformer

LocoFormer - Generalist Locomotion via Long-Context Adaptation

Score
73
★ 118 ⑂ 6 +2/day
Python
lucidrains
lucidrains
taylor-series-linear-attention

Explorations into the recently proposed Taylor Series Linear Attention

Score
0
★ 100 ⑂ 3
Python
lucidrains
lucidrains
zorro-pytorch

Implementation of Zorro, Masked Multimodal Transformer, in Pytorch

Score
18
★ 98 ⑂ 5
Python
kyegomez
kyegomez
SparseAttention

Pytorch Implementation of the sparse attention from the paper: "Generating Long Sequences with Sparse Transformers"

Score
70
★ 97 ⑂ 6
Python
lucidrains
lucidrains
agent-attention-pytorch

Implementation of Agent Attention in Pytorch

Score
14
★ 93 ⑂ 5
Python
lucidrains
lucidrains
complex-valued-transformer

Implementation of the transformer proposed in "Building Blocks for a Complex-Valued Transformer Architecture"

Score
16
★ 92 ⑂ 7
Python
johnsmithm
johnsmithm
multi-heads-attention-image-classification

Multi heads attention for image classification

Score
20
★ 80 ⑂ 33
Python
lucidrains
lucidrains
transframer-pytorch

Implementation of Transframer, Deepmind's U-net + Transformer architecture for up to 30 seconds video generation, in Pytorch

Score
11
★ 72 ⑂ 5
Python
lucidrains
lucidrains
transformer-directed-evolution

Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster

Score
59
★ 71 ⑂ 0
Python
lucidrains
lucidrains
equiformer-diffusion

Implementation of Denoising Diffusion for protein design, but using the new Equiformer (successor to SE3 Transformers) with some additional improvements

Score
9
★ 57 ⑂ 4
lucidrains
lucidrains
flash-genomics-model

My own attempt at a long context genomics model, leveraging recent advances in long context attention modeling (Flash Attention + other hierarchical methods)

Score
7
★ 54 ⑂ 5
Python
lucidrains
lucidrains
pause-transformer

Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount of time on any token

Score
5
★ 53 ⑂ 1
Python
lucidrains
lucidrains
coordinate-descent-attention

Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk

Score
0
★ 47 ⑂ 2
Python
lucidrains
lucidrains
autoregressive-linear-attention-cuda

CUDA implementation of autoregressive linear attention, with all the latest research findings

Score
2
★ 46 ⑂ 3
Python
Related Topics
#artificial-intelligence#deep-learning#transformers#attention-is-all-you-need#attention-mechanism#computer-vision#machine-learning#denoising-diffusion#video-generation#long-context#linear-attention#reinforcement-learning

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly