News for hackers. Stuff that matters.

A comment on OPT: Open Pre-trained Transformer Language Models. Parent comment

Re:OPT: Open Pre-trained Transformer Language Models by JoeyBananas on Tuesday May 03, 2022 @09:53AM (#31248322)
A 175B parameter language model is going to be huge. You probably don't want the biggest model just for messing around.
[ Parent | on HN ]

There are no comments on this comment yet.