Add TF weights

#1
by joaogante HF staff - opened

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=3.529e-05; Maximum crossload hidden layer difference=1.526e-04;
Maximum conversion output difference=3.529e-05; Maximum conversion hidden layer difference=1.526e-04;

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

Online Language Modelling org

LGTM, thanks

Tristan changed pull request status to merged

Sign up or log in to comment