%0 Journal Article %1 journals/corr/abs-2112-06905 %A Du, Nan %A Huang, Yanping %A Dai, Andrew M. %A Tong, Simon %A Lepikhin, Dmitry %A Xu, Yuanzhong %A Krikun, Maxim %A Zhou, Yanqi %A Yu, Adams Wei %A Firat, Orhan %A Zoph, Barret %A Fedus, Liam %A Bosma, Maarten %A Zhou, Zongwei %A Wang, Tao %A Wang, Yu Emma %A Webster, Kellie %A Pellat, Marie %A Robinson, Kevin %A Meier-Hellstern, Kathy %A Duke, Toju %A Dixon, Lucas %A Zhang, Kun %A Le, Quoc V. %A Wu, Yonghui %A Chen, Zhifeng %A Cui, Claire %D 2021 %J CoRR %K dblp %T GLaM: Efficient Scaling of Language Models with Mixture-of-Experts. %U http://dblp.uni-trier.de/db/journals/corr/corr2112.html#abs-2112-06905 %V abs/2112.06905

@article{journals/corr/abs-2112-06905, added-at = {2023-08-16T00:00:00.000+0200}, author = {Du, Nan and Huang, Yanping and Dai, Andrew M. and Tong, Simon and Lepikhin, Dmitry and Xu, Yuanzhong and Krikun, Maxim and Zhou, Yanqi and Yu, Adams Wei and Firat, Orhan and Zoph, Barret and Fedus, Liam and Bosma, Maarten and Zhou, Zongwei and Wang, Tao and Wang, Yu Emma and Webster, Kellie and Pellat, Marie and Robinson, Kevin and Meier-Hellstern, Kathy and Duke, Toju and Dixon, Lucas and Zhang, Kun and Le, Quoc V. and Wu, Yonghui and Chen, Zhifeng and Cui, Claire}, biburl = {https://www.bibsonomy.org/bibtex/225291f28d2d80ac095409934a8611b17/dblp}, ee = {https://arxiv.org/abs/2112.06905}, interhash = {4b1e9dd5ba5f9996369c96bec5cb3580}, intrahash = {25291f28d2d80ac095409934a8611b17}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T22:22:48.000+0200}, title = {GLaM: Efficient Scaling of Language Models with Mixture-of-Experts.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2112.html#abs-2112-06905}, volume = {abs/2112.06905}, year = 2021 }