Repositories

lucidrains repositories

402 supported repositories

Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper

Last commit Oct 30, 2021

 (82 stars) (8 forks) (0 indexed issues) (0 open good first issues)

Implementation and explorations into PopuLoRA, Co-Evolving LLM Populations for Reasoning Self-Play

Last commit Jun 3, 2026

 (12 stars) (0 forks) (0 indexed issues) (0 open good first issues)

An implementation of PPO in Pytorch

Last commit May 19, 2026

 (125 stars) (11 forks) (0 indexed issues) (0 open good first issues)

Standalone Product Key Memory module in Pytorch - for augmenting Transformer models

Last commit Nov 1, 2025

 (87 stars) (5 forks) (0 indexed issues) (0 open good first issues)

Implementation and replication of ProGen, Language Modeling for Protein Generation, in Jax

Last commit Sep 8, 2021

 (114 stars) (17 forks) (0 indexed issues) (0 open good first issues)

Implementation of ProteinBERT in Pytorch

Last commit Aug 10, 2021

 (165 stars) (20 forks) (0 indexed issues) (0 open good first issues)

Implementation of the pseudo projector proposed by Vitaly Bulgakov at Mass General Brigham

Last commit Apr 20, 2026

 (9 stars) (0 forks) (0 indexed issues) (0 open good first issues)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Last commit Aug 16, 2022

 (5 stars) (0 forks) (0 indexed issues) (0 open good first issues)

Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new AI research

Last commit Jul 26, 2024

 (126 stars) (4 forks) (0 indexed issues) (0 open good first issues)

torch-optimizer -- collection of optimizers for Pytorch

Last commit Mar 2, 2020

 (7 stars) (0 forks) (0 indexed issues) (0 open good first issues)

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

Last commit Jun 20, 2025

 (407 stars) (22 forks) (0 indexed issues) (0 open good first issues)

Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)

Last commit Mar 25, 2025

 (55 stars) (0 forks) (0 indexed issues) (0 open good first issues)

Implementation of rectified flow and some of its followup research / improvements in Pytorch

Last commit Jun 3, 2026

 (464 stars) (32 forks) (0 indexed issues) (0 open good first issues)

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

Last commit Feb 14, 2024

 (208 stars) (14 forks) (1 indexed issue) (1 open good first issue)

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

Last commit Jan 6, 2025

 (423 stars) (19 forks) (0 indexed issues) (0 open good first issues)

Deep Recurrent Neural Networks and LSTMs in Javascript. More generally also arbitrary expression graphs with automatic differentiation.

Last commit Jul 7, 2015

 (9 stars) (1 fork) (0 indexed issues) (0 open good first issues)

Reformer, the efficient Transformer, in Pytorch

Last commit Jun 21, 2023

 (2,192 stars) (253 forks) (0 indexed issues) (0 open good first issues)

Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012

Last commit Apr 6, 2022

 (49 stars) (6 forks) (0 indexed issues) (0 open good first issues)

Implementation of the Remixer Block from the Remixer paper, in Pytorch

Last commit Sep 27, 2021

 (36 stars) (1 fork) (0 indexed issues) (0 open good first issues)

Implementation of ResMLP, an all MLP solution to image classification, in Pytorch

Last commit Jun 3, 2021

 (200 stars) (32 forks) (0 indexed issues) (0 open good first issues)