Update TF weights
#3
by
joaogante
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=1.001e-05; Maximum crossload hidden layer difference=7.629e-06;
Maximum conversion output difference=1.001e-05; Maximum conversion hidden layer difference=7.629e-06;
The logits bias were not being stored and loaded in TF. The following GH PR fixes it, and this Hub PR adds the missing weights :)
joaogante
changed pull request status to
merged