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=3.625e-04; Maximum converted output difference=3.625e-04.

All crossload differences

logits: 3.147e-05
hidden_states[0]: 1.669e-05
hidden_states[1]: 8.945e-05
hidden_states[2]: 3.625e-04
hidden_states[3]: 2.117e-04
hidden_states[4]: 8.869e-05

amyeroberts changed pull request status to merged