HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by fishpham | Hacker News Reader
Parent
Full thread
fishpham
·
Those won’t be sufficient to run SOTA/trillion parameter models
View on HN
Zambyte
·
And most tasks don't demand that.
general1465
·
Distilled models are good enough.
Reply on news.ycombinator.com