add auto mapping to preprocessor_config for opportunity to use model after save_pretrained

#13

Thank you for the great model!

I found a small issue with processor saving. It can be successfully loaded using model id from the hub, but can not be restored after processor.save_pretrained call due to removing info about automapping in processor_config.json (as both preprocessor_config and processor_config reference for the same class and class object configuration overrides this info based on preprocessor_config). Adding auto_mapping to preprocessing_config helps to resolve this issue.

Could you please take a look?
This is helpful for possibility to integrate model to optimum

sthyland changed pull request status to merged
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment