Document Preview Unavailable
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
Shoeybi, Mohammad; Patwary, Mostofa; Puri, Raul; LeGresley, Patrick; Casper, Jared; et al. arXiv.org, Mar 13, 2020.You might have access to this document
-
Try and log in through your institution to see if they have access to the full text.
Log in through your library