BEN2 pruning test # 1 - distillation

Original parameters: 94,134,658

Pruned parameters: 36,275,254

Parameter reduction: 61.5%

  • Swin Transformer depths: [2, 2, 18, 2] โ†’ [2, 2, 6, 2]
  • Swin Transformer heads: [4, 8, 16, 32] โ†’ [3, 6, 12, 24]

distill loss: 0.0008

Downloads last month
7
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support