Nvidia released a paper about a 100KB text-to-image model that only trained for 4 minutes but claims to be better than bigger models
hayek @ hayek @feddit.de Posts 1Comments 2Joined 2 yr. ago
hayek @ hayek @feddit.de
Posts
1
Comments
2
Joined
2 yr. ago
Can’t wait for the first X on X by X Æ A-12 about the SpaceX launch