Add TF weights
#2
by neggles - 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=3.815e-06; Maximum crossload hidden layer difference=1.733e-02;
Maximum conversion output difference=3.815e-06; Maximum conversion hidden layer difference=1.733e-02;
CAUTION: The maximum admissible error was manually increased to 0.1!
See GitHub PR #25558 for details, precision overridden due to hidden states being a little weird in TF; final output logits are within 1.788e-05 for all model variants/sizes.