Add TF weights

#2
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=3.448e-03; Maximum crossload hidden layer difference=1.855e-02;
Maximum conversion output difference=3.448e-03; Maximum conversion hidden layer difference=1.855e-02;

cc @patrickvonplaten [HF maintainer(s) for this repo]

patrickvonplaten changed pull request status to merged

Sign up or log in to comment