logoalt Hacker News

dotancohentoday at 7:36 AM1 replyview on HN

Can you back this up with documentation? I don't believe that this is the case.


Replies

pixelmelttoday at 8:24 AM

Check out Unsloths REAP models, you can outright delete a few of the lesser used experts without the model going braindead since they all can handle each token but some are better posed to do so.