Article 6HNJA LiteLlama-460M-1T has 460M parameters trained with 1T tokens

LiteLlama-460M-1T has 460M parameters trained with 1T tokens

by
from Hacker News on (#6HNJA)
Story ImageComments
External Content
Source RSS or Atom Feed
Feed Location http://news.ycombinator.com/rss
Feed Title Hacker News
Feed Link https://news.ycombinator.com/
Reply 0 comments