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=1.020e-04; Maximum crossload hidden layer difference=1.621e-05;
Maximum conversion output difference=1.020e-04; Maximum conversion hidden layer difference=1.621e-05;

CAUTION: The maximum admissible error was manually increased to 0.0002!

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

Sign up or log in to comment