Add TF weights

#1
by amyeroberts 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=8.914e-04; Maximum converted output difference=8.914e-04.

All crossload differences

logits: 3.719e-05
hidden_states[0]: 1.907e-05
hidden_states[1]: 1.310e-04
hidden_states[2]: 4.309e-04
hidden_states[3]: 8.914e-04
hidden_states[4]: 8.297e-05

amyeroberts changed pull request status to merged

Sign up or log in to comment