Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its PyTorch counterpart.

Maximum crossload output difference=1.574e-05; Maximum crossload hidden layer difference=4.150e-03;
Maximum conversion output difference=1.574e-05; Maximum conversion hidden layer difference=4.150e-03;

CAUTION: The maximum admissible error was manually increased to 0.01!

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment