Closed pglock closed 5 years ago
Oops thanks for the heads up I had forgottne to commit and push the fix. Try pulling the branch paul
from https://github.com/pmichel31415/pytorch-pretrained-BERT , the problem should be fixed (feel free to reopen this issue if you run into any other problem)
Hi,
thanks for your code! The pruning works great using masking. However, when I tried to actually prune the model to see, if there's a speedup, it fails.
new_layer
inprune_linear_layer
has to be moved to the correct device.