AR Vision

Hi @NielsRogge and thank you very much for your work! I have also tried to fine-tune the `microsoft/udop-large-512-300k` model following the steps in [demo notebook](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/UDOP/Fine_tune_UDOP_on_a_custom_dataset_(JSON_extraction).ipynb), using the default configuration. However,...

Perfect! Thank you very much for your response! I have seen that you have added new notebooks for training in different tasks, starting from those base models. Would it be...

any solution to this?

But this is just for inference, right? the models that are uploaded to hugging face transformers. Is there a notebook for fine-tuning?