%0 Journal Article %1 journals/corr/abs-2305-14705 %A Shen, Sheng %A Hou, Le %A Zhou, Yanqi %A Du, Nan %A Longpre, Shayne %A Wei, Jason %A Chung, Hyung Won %A Zoph, Barret %A Fedus, William %A Chen, Xinyun %A Vu, Tu %A Wu, Yuexin %A Chen, Wuyang %A Webson, Albert %A Li, Yunxuan %A Zhao, Vincent Y. %A Yu, Hongkun %A Keutzer, Kurt %A Darrell, Trevor %A Zhou, Denny %D 2023 %J CoRR %K dblp %T Flan-MoE: Scaling Instruction-Finetuned Language Models with Sparse Mixture of Experts. %U http://dblp.uni-trier.de/db/journals/corr/corr2305.html#abs-2305-14705 %V abs/2305.14705

@article{journals/corr/abs-2305-14705, added-at = {2024-02-27T00:00:00.000+0100}, author = {Shen, Sheng and Hou, Le and Zhou, Yanqi and Du, Nan and Longpre, Shayne and Wei, Jason and Chung, Hyung Won and Zoph, Barret and Fedus, William and Chen, Xinyun and Vu, Tu and Wu, Yuexin and Chen, Wuyang and Webson, Albert and Li, Yunxuan and Zhao, Vincent Y. and Yu, Hongkun and Keutzer, Kurt and Darrell, Trevor and Zhou, Denny}, biburl = {https://www.bibsonomy.org/bibtex/24647c1e7b426963a361a06dfaa1d745f/dblp}, ee = {https://doi.org/10.48550/arXiv.2305.14705}, interhash = {d19c842b990262c994edff61a2d60ed3}, intrahash = {4647c1e7b426963a361a06dfaa1d745f}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T23:58:13.000+0200}, title = {Flan-MoE: Scaling Instruction-Finetuned Language Models with Sparse Mixture of Experts.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2305.html#abs-2305-14705}, volume = {abs/2305.14705}, year = 2023 }