%0 Journal Article %1 journals/corr/abs-2401-06066 %A Dai, Damai %A Deng, Chengqi %A Zhao, Chenggang %A Xu, R. X. %A Gao, Huazuo %A Chen, Deli %A Li, Jiashi %A Zeng, Wangding %A Yu, Xingkai %A Wu, Y. %A Xie, Zhenda %A Li, Y. K. %A Huang, Panpan %A Luo, Fuli %A Ruan, Chong %A Sui, Zhifang %A Liang, Wenfeng %D 2024 %J CoRR %K dblp %T DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models. %U http://dblp.uni-trier.de/db/journals/corr/corr2401.html#abs-2401-06066 %V abs/2401.06066

@article{journals/corr/abs-2401-06066, added-at = {2024-01-25T00:00:00.000+0100}, author = {Dai, Damai and Deng, Chengqi and Zhao, Chenggang and Xu, R. X. and Gao, Huazuo and Chen, Deli and Li, Jiashi and Zeng, Wangding and Yu, Xingkai and Wu, Y. and Xie, Zhenda and Li, Y. K. and Huang, Panpan and Luo, Fuli and Ruan, Chong and Sui, Zhifang and Liang, Wenfeng}, biburl = {https://www.bibsonomy.org/bibtex/2b21e8e76a2be29b069f6add442908ec5/dblp}, ee = {https://doi.org/10.48550/arXiv.2401.06066}, interhash = {233f30fbf931ddbed2fc69e6b81470e4}, intrahash = {b21e8e76a2be29b069f6add442908ec5}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T23:13:29.000+0200}, title = {DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2401.html#abs-2401-06066}, volume = {abs/2401.06066}, year = 2024 }