Add TF weights

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=6.116e-03; Maximum crossload hidden layer difference=9.521e-03;
Maximum conversion output difference=6.116e-03; Maximum conversion hidden layer difference=9.521e-03;

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

@sanchit-gandhi could you take a look please?

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

Sign up or log in to comment