Wrappers around environments that will take care of providing representations from self supervised learning automagically
(8 stars) (0 forks) (0 indexed issues) (0 open good first issues)
Repositories
lucidrains repositories
Implementation of Denoising Diffusion for protein design, but using the new Equiformer (successor to SE3 Transformers) with some additional improvements
(57 stars) (4 forks) (0 indexed issues) (0 open good first issues)
Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein folding
(290 stars) (31 forks) (0 indexed issues) (0 open good first issues)
lucidrains/equinoxPython
Callable PyTrees and filtered JIT/grad transformations => neural networks in JAX.
(4 stars) (1 fork) (0 indexed issues) (0 open good first issues)
An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols
(16 stars) (2 forks) (0 indexed issues) (0 open good first issues)
Implementation of the algorithm detailed in paper "Evolutionary design of molecules based on deep learning and a genetic algorithm"
(24 stars) (2 forks) (0 indexed issues) (0 open good first issues)
Pytorch implementation of Evolutionary Policy Optimization, from Wang et al. of the Robotics Institute at Carnegie Mellon University
(111 stars) (4 forks) (0 indexed issues) (0 open good first issues)
Implementation of Fast Transformer in Pytorch
(176 stars) (15 forks) (0 indexed issues) (0 open good first issues)
Implementation of Fast Weight Attention
(31 stars) (1 fork) (0 indexed issues) (0 open good first issues)
Implementation of Fast Weight Product Key Memories
(5 stars) (0 forks) (0 indexed issues) (0 open good first issues)
Implementation of the fast weight product key memory from Sakana AI
(18 stars) (1 fork) (0 indexed issues) (0 open good first issues)
Implementation of Feedback Transformer in Pytorch
(108 stars) (2 forks) (0 indexed issues) (0 open good first issues)
lucidrains/ffcvPython
FFCV: Fast Forward Computer Vision (and other ML workloads!)
(6 stars) (1 fork) (0 indexed issues) (0 open good first issues)
lucidrains/firefly-torchPython
Exploration into the Firefly algorithm in Pytorch
(41 stars) (2 forks) (0 indexed issues) (0 open good first issues)
Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch
(1,267 stars) (66 forks) (0 indexed issues) (0 open good first issues)
Fast and memory-efficient exact attention
(20 stars) (5 forks) (0 indexed issues) (0 open good first issues)
Implementation of Flash Attention in Jax
(227 stars) (25 forks) (0 indexed issues) (0 open good first issues)
Implementation of fused cosine similarity attention in the same style as Flash Attention
(220 stars) (12 forks) (0 indexed issues) (0 open good first issues)
My own attempt at a long context genomics model, leveraging recent advances in long context attention modeling (Flash Attention + other hierarchical methods)
(54 stars) (5 forks) (0 indexed issues) (0 open good first issues)
Implementation of the video diffusion model and training scheme presented in the paper, Flexible Diffusion Modeling of Long Videos, in Pytorch
(85 stars) (2 forks) (0 indexed issues) (0 open good first issues)