News for hackers. Stuff that matters.

A comment on T0* – Series of encoder-decoder models trained on a large set of different tasks. Parent comment

Re:T0* – Series of encoder-decoder models trained on a large... by srush on Monday October 18, 2021 @12:27PM (#28907322)
While in theory it could, the nature of its training favors shorter more factual replies.
[ Parent | on HN ]

There are no comments on this comment yet.