Add TF weights
#7
by Rocketknight1 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=1.395e-03; Maximum crossload hidden layer difference=1.080e+00;
Maximum conversion output difference=1.395e-03; Maximum conversion hidden layer difference=1.080e+00;
CAUTION: The maximum admissible error was manually increased to 2.0!
Thanks!
ybelkada changed pull request status to merged
Hi, @Rocketknight1 , can you instruct more how can I load this blip model in tensorflow version? Thanks!