Yoni Gozlan

> @yonigozlan tiny models aren't automatically generated, those are all manually created. Rather than modifying an existing one (which might break existing tests), I'd suggest just making a new tiny...

@ArthurZucker Addressed your comments! I tried to simplify the code a bit without removing any logic. Happy to remove some logic depending on what you think about this https://github.com/huggingface/transformers/pull/34170#discussion_r1816953666

Clearly agree that we should rely on the processors. I can make all this logic into a utils or a ProcessorMixin function and adapt it a bit for models requiring...

@ArthurZucker I removed most of the preprocessing logic, hopefully the code should be less messy now :)

> Not sure why I didn't see this failure on CircleCI, but running on daily CI runner, I got > > > FAILED tests/models/fuyu/test_modeling_fuyu.py::FuyuModelTest::test_pipeline_image_text_to_text - TypeError: 'int' object is not...

@ArthurZucker There were some issues with other multimodal pipelines tests where model tests weren't actually being performed previously. I added the tests and made some modifications to owlv2 and fuyu...

Thanks for all of your inputs! I'll merged this now as the remaining issues/improvements raised seem a bit out of scope for this PR. Just to recap some of the...

Hi @SangbumChoi ! Sorry for the delay on this, I have started reviewing and will continue this week. I'm happy to help push updates to get up to speed with...

@SangbumChoi Sounds good! I'll review + push some changes in the meantime then, let's see if I get to the video part by June 5 😅. Thanks again for your...

Hi @yaswanth19 ! Is this ready for a review? Feel free to ping me when it is!