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=9.537e-06; Maximum crossload hidden layer difference=2.441e-04;
Maximum conversion output difference=9.537e-06; Maximum conversion hidden layer difference=2.441e-04;

CAUTION: The maximum admissible error was manually increased to 0.001!

sgugger changed pull request status to merged

Sign up or log in to comment