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=2.384e-07; Maximum crossload hidden layer difference=3.815e-06;
Maximum conversion output difference=2.384e-07; Maximum conversion hidden layer difference=3.815e-06;

cheerfun changed pull request status to closed

Sign up or log in to comment