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=1.454e-05; Maximum crossload hidden layer difference=1.144e-05;
Maximum conversion output difference=1.454e-05; Maximum conversion hidden layer difference=1.144e-05;

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 :)

https://github.com/huggingface/transformers/pull/18833

joaogante changed pull request status to merged

Sign up or log in to comment