%0 Journal Article %1 journals/corr/abs-2208-03306 %A Li, Margaret %A Gururangan, Suchin %A Dettmers, Tim %A Lewis, Mike %A Althoff, Tim %A Smith, Noah A. %A Zettlemoyer, Luke %D 2022 %J CoRR %K dblp %T Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models. %U http://dblp.uni-trier.de/db/journals/corr/corr2208.html#abs-2208-03306 %V abs/2208.03306

@article{journals/corr/abs-2208-03306, added-at = {2022-08-10T00:00:00.000+0200}, author = {Li, Margaret and Gururangan, Suchin and Dettmers, Tim and Lewis, Mike and Althoff, Tim and Smith, Noah A. and Zettlemoyer, Luke}, biburl = {https://www.bibsonomy.org/bibtex/281bee6e4fe34934ecd0f4921739db2b4/dblp}, ee = {https://doi.org/10.48550/arXiv.2208.03306}, interhash = {a229f5bb15afcbe0d405b2e09ad051f5}, intrahash = {81bee6e4fe34934ecd0f4921739db2b4}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T22:58:15.000+0200}, title = {Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2208.html#abs-2208-03306}, volume = {abs/2208.03306}, year = 2022 }