%0 Generic %1 hoffmann2022training %A Hoffmann, Jordan %A Borgeaud, Sebastian %A Mensch, Arthur %A Buchatskaya, Elena %A Cai, Trevor %A Rutherford, Eliza %A de Las Casas, Diego %A Hendricks, Lisa Anne %A Welbl, Johannes %A Clark, Aidan %A Hennigan, Tom %A Noland, Eric %A Millican, Katie %A van den Driessche, George %A Damoc, Bogdan %A Guy, Aurelia %A Osindero, Simon %A Simonyan, Karen %A Elsen, Erich %A Rae, Jack W. %A Vinyals, Oriol %A Sifre, Laurent %D 2022 %K ai %T Training Compute-Optimal Large Language Models

@misc{hoffmann2022training, added-at = {2024-05-09T19:26:08.000+0200}, archiveprefix = {arXiv}, author = {Hoffmann, Jordan and Borgeaud, Sebastian and Mensch, Arthur and Buchatskaya, Elena and Cai, Trevor and Rutherford, Eliza and de Las Casas, Diego and Hendricks, Lisa Anne and Welbl, Johannes and Clark, Aidan and Hennigan, Tom and Noland, Eric and Millican, Katie and van den Driessche, George and Damoc, Bogdan and Guy, Aurelia and Osindero, Simon and Simonyan, Karen and Elsen, Erich and Rae, Jack W. and Vinyals, Oriol and Sifre, Laurent}, biburl = {https://www.bibsonomy.org/bibtex/2ab3f4ffbe668e655bf873670d465e6b4/nebuchadnezzar}, description = {Training Compute-Optimal Large Language Models}, eprint = {2203.15556}, interhash = {fbb961ee37f6133cb08168e7c017184e}, intrahash = {ab3f4ffbe668e655bf873670d465e6b4}, keywords = {ai}, primaryclass = {cs.CL}, timestamp = {2024-05-09T19:26:08.000+0200}, title = {Training Compute-Optimal Large Language Models}, year = 2022 }