logoalt Hacker News

aboardRat4 • yesterday at 11:02 PM • 2 replies • view on HN

>m getting fatigued with the constant introduction of names and the impenetrability of mapping these brand new names to use cases.

Because probably there is no system. They just train a model, and find out that it's "kinda good", and that's it, they publish it. The models do not constitute even a partially ordered set, nobody can predict their ranking for your particular tasks.


Replies

motbus3 • yesterday at 11:36 PM

Like some vendors, making the name scheme incomprehensible is part of you not knowing which one is the best cost benefit

➕ show 2 replies
floatingtorch • today at 1:51 AM

There is definitely a system. They are training models of different sizes for different levels of inference efficiency, which maps to token pricing. The ordered set is the size of the weights/ computational complexity during inference.