nvidia

/

mit-b5

like 8

Follow

NVIDIA 3,396

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=5.722e-06; Maximum crossload hidden layer difference=1.011e-04;
Maximum conversion output difference=5.722e-06; Maximum conversion hidden layer difference=1.011e-04;