lucidrains/meshPython
Mesh TensorFlow: Model Parallelism Made Easier
(2 stars) (1 fork) (0 indexed issues) (0 open good first issues)
Repositories
lucidrains repositories
Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch
(861 stars) (68 forks) (0 indexed issues) (0 open good first issues)
lucidrains/metacontrollerJupyter Notebook
Implementation of the MetaController proposed in "Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning" from the Paradigms of Intelligence team at Google
(105 stars) (13 forks) (0 indexed issues) (0 open good first issues)
Implementation of Metaformer, but in an autoregressive manner
(26 stars) (5 forks) (0 indexed issues) (0 open good first issues)
Implementation of MetNet-3, SOTA neural weather model out of Google Deepmind, in Pytorch
(241 stars) (28 forks) (0 indexed issues) (0 open good first issues)
lucidrains/mimic-videoPython
Implementation of Mimic-Video, Video-Action Models for SOTA Generalizable Robot Control Beyond VLAs
(110 stars) (6 forks) (0 indexed issues) (0 open good first issues)
Implementation of the proposed minGRU in Pytorch
(324 stars) (24 forks) (0 indexed issues) (0 open good first issues)
Implementation of Mind Evolution, Evolving Deeper LLM Thinking, from Deepmind
(59 stars) (4 forks) (0 indexed issues) (0 open good first issues)
Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch
(92 stars) (2 forks) (0 indexed issues) (0 open good first issues)
Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts
(122 stars) (4 forks) (0 indexed issues) (0 open good first issues)
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
(859 stars) (71 forks) (0 indexed issues) (0 open good first issues)
lucidrains/mlm-pytorchPython
An implementation of masked language modeling for Pytorch, made as concise and simple as possible
(181 stars) (24 forks) (0 indexed issues) (0 open good first issues)
lucidrains/mlp-gpt-jaxPython
A GPT, made only of MLPs, in Jax
(59 stars) (1 fork) (0 indexed issues) (0 open good first issues)
An All-MLP solution for Vision, from Google AI
(1,060 stars) (107 forks) (0 indexed issues) (0 open good first issues)
lucidrains/mmditPython
Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch
(536 stars) (16 forks) (0 indexed issues) (0 open good first issues)
lucidrains/mogrifierPython
Usable implementation of Mogrifier, a circuit for enhancing LSTMs and potentially other networks, from Deepmind
(22 stars) (0 forks) (0 indexed issues) (0 open good first issues)
Pytorch reimplementation of Molecule Attention Transformer, which uses a transformer to tackle the graph-like structure of molecules
(58 stars) (7 forks) (0 indexed issues) (0 open good first issues)
Multi-Joint dynamics with Contact. A general purpose physics simulator.
(1 star) (0 forks) (0 indexed issues) (0 open good first issues)
Implementation of a multimodal diffusion transformer in Pytorch
(108 stars) (2 forks) (0 indexed issues) (0 open good first issues)
lucidrains/multiscreenPython
Implementation of Multiscreen proposed by Ken Nakanishi for "Screening is Enough"
(15 stars) (1 fork) (0 indexed issues) (0 open good first issues)