Unconventional AI
@unconvAI
We removed 93.25% of the connections in our Un-0 image model, fully expecting to pay for it in quality. But it got better.
FID 7.15 on ImageNet 64x64, roughly 1.9 ahead of the dense baseline at matched size. Same family of model, a fraction of the couplings, a better score.
Here
FID 7.15 on ImageNet 64x64, roughly 1.9 ahead of the dense baseline at matched size. Same family of model, a fraction of the couplings, a better score.
Here
0:12 5 190