Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

A 175 billion parameter model might be a couple hundred gigs on disk. The file is probably just too big for GitHub/other standard FB services.


They could just torrent.


They could, and their might be a torrent in the future - but torrents lose tracking info. I'm sure the researchers want to know who is downloading their models even if they don't care who it is.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: