From the paper it appears that it's probably more useful on small-ish models. | alt Hacker News

alt Hacker News

nullc • yesterday at 11:46 PM • 1 reply • view on HN

From the paper it appears that it's probably more useful on small-ish models.

Replies

lwansbrough • today at 1:08 AM

What does it cost to train a model like 1-bit Bonsai? Anyone know?