lucidrains/mixture-of-experts
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
PythonMIT
Stargazers
- abodacsOpenCoast
- adelevie@casetext
- alreadydoneHeidelberg / Shenzhen
- bishengSoutheast University
- carmanzhangPhD student
- eltonzheng
- Epsilon-LeeIndependent thinker
- evanzdShanghai, China
- fly51flyPRIS
- fox-gamer
- fwu-asapp
- ghosthamletThe Rest Is Silence of Code
- iso-p
- jacobdanovitchMicrosoft
- jeffhsu3Ivy Natal
- kaiwangm@Tencent
- kiminh
- lorenlugosch
- mehdidcJuelich Supercomputing Center (JSC), Forschungszentrum Jülich GmbH, LAION
- mjsML@NVIDIA
- mnmjh1215
- Nowhitestar
- numb3r3@jina-ai
- Ottovonxu
- PhilippMarquardt
- postBGBobidi
- rcshubhadeepGoa
- sdtblck
- stjordanisGreece
- SungMinChoCMALAB, Seoul National University
- tboquet@Mistplay
- tristanz@continual-ai
- vedant
- willwilliams
- ykim362Microsoft
- yurakuratov