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=2.484e-04; Maximum crossload hidden layer difference=6.744e-03;
Maximum conversion output difference=2.484e-04; Maximum conversion hidden layer difference=6.744e-03;

CAUTION: The maximum admissible error was manually increased to 1.0!

sanchit-gandhi changed pull request status to merged

Sign up or log in to comment