undefined | Better HN

0 pointsvaline2y ago0 comments

How much data do you need for UNA? Is a typical fine tuning dataset needed or can you get away with less than that?

0 comments

In addition to what was said, if its anything like DPO you don't need a lot of data, just a good set. For instance, DPO requires "good" and "bad" responses for each given prompt.

fblgit2y ago

doesn't require much data, in a 7B can take a couple hours ~

valineOP2y ago

That’s cool. A couple hours on a single GPU or like 8x a100s?

j / k navigate · click thread line to collapse