GallagherCommaJack/mixture-of-experts
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
PythonMIT
No issues in this repository yet.
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
PythonMIT
No issues in this repository yet.