Apostol Andrei

Not getting any speedup when using adapters for DistilBert over regular fine-tuning

1

Hello, I'm comparing the speedup & accuracy tradeoff I can get on a `Distilbert` model. During my trials, I seem to not have noticed any speedup using any of the...

Low training accuracy using pre-trained model

2

Hello, I am trying to evaluate a pre-trained mobilenetv2 model from torchvision on the ImageNet training dataset using this script. To do so, I modify lines 235-237 to perform validation...

Not really an issue, but I'd like to cite this repository in my paper. I'd like to ask the author whether he would like to have his name included in...