@misc{shen2023flan,
  title={Flan-MoE: Scaling Instruction-Finetuned Language Models with Sparse Mixture of Experts},
  author={Sheng Shen and Le Hou and Yanqi Zhou and Nan Du and Shayne Longpre and Jason Wei and Hyung Won Chung and Barret Zoph and William Fedus and Xinyun Chen and Tu Vu and Yuexin Wu and Wuyang Chen and Albert Webson and Yunxuan Li and Vincent Zhao and Hongkun Yu and Kurt Keutzer and Trevor Darrell and Denny Zhou},
  year={2023},
  eprint={2305.14705},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2305.14705}
}