Monday, October 11, 2021

Megatron-Turing NLG 530B, the World’s Largest Generative Language Model

Article URL: https://www.microsoft.com/en-us/research/blog/using-deepspeed-and-megatron-to-train-megatron-turing-nlg-530b-the-worlds-largest-and-most-powerful-generative-language-model/

Comments URL: https://news.ycombinator.com/item?id=28831917

Points: 2

# Comments: 0



from Hacker News: Newest https://ift.tt/3DprzKa
via IFTTT

No comments:

Post a Comment

Starlink satellites create light pollution and disrupt radio frequencies

Article URL: https://www.cbc.ca/news/science/spacex-starlinks-astronomy-1.7334803 Comments URL: https://news.ycombinator.com/item?id=417520...