St Moe Pytorch Save Abandoned

ST-MoE - Pytorch (wip)

Implementation of ST-MoE, the final incarnation of mixture of experts after years of research at Brain, in Pytorch. Will be largely a transcription of the official Mesh Tensorflow implementation. If you have any papers you think should be added, while I have my attention on mixture of experts, please open an issue.

Citations

@inproceedings{Zoph2022STMoEDS,
    title   = {ST-MoE: Designing Stable and Transferable Sparse Expert Models},
    author  = {Barret Zoph and Irwan Bello and Sameer Kumar and Nan Du and Yanping Huang and Jeff Dean and Noam M. Shazeer and William Fedus},
    year    = {2022}
}