| knowledge-distillation-on-cifar-100 | resnet8x4 (T: resnet32x4 S: resnet8x4) | #9 | Top-1 Accuracy (%): 76.68 |
| knowledge-distillation-on-cifar-100 | vgg8 (T:vgg13 S:vgg8) | #15 | Top-1 Accuracy (%): 74.93 |
| knowledge-distillation-on-cifar-100 | resnet110 (T:resnet110 S:resnet20) | #21 | Top-1 Accuracy (%): 71.99 |
| knowledge-distillation-on-imagenet | ITRD (T: ResNet-34 S:ResNet-18) | #41 | Top-1 accuracy %: 71.68model size: 11.69MCRD training setting: ✓ |
| question-answering-on-squad11 | BERT - 6 Layers | #10 | EM: 81.5F1: 88.5 |
| question-answering-on-squad11 | BERT - 3 Layers | #17 | EM: 77.7F1: 85.8 |