Training Compute-Optimal Large Language Models
Hoffmann, Jordan, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, et al. 2022. “Training Compute-Optimal Large Language Models.” arXiv:2203.15556 [cs.CL]. arxiv.org/abs/2203.15556
BibTeX
@misc{hoffmann2022training,
title = {Training Compute-Optimal Large Language Models},
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},
year = 2022,
eprint = {2203.15556},
primaryclass = {cs.CL},
archiveprefix = {arXiv}
}