Yoni Gozlan

@Cyrilvallez The image processor is quite different from anything we have at the moment, as maskformer and mask2former don't have a fast image processor yet. However some modular refactoring should...

> LGTM. Just wondering about some models where we had no lancsoz resampling. Do we get the closest resampling in those cases and are the diffs small enough? Good point...

Hey @amyeroberts @qubvel ! I think this PR is ready for a first review. What's missing for now is adding/modifying tests (current ones are for Grounding Dino and not adapted...

Hi @amyeroberts and @qubvel! When you have some time, could you please take another look at this PR? I've resolved your previous remarks and left the ones where I had...

Thanks for the review @qubvel ! For the `OmdetTurboModel`, the task specific part of the model starts at the very beginning of the decoder, where there are two heads defined,...

Hey @VladOS95-cyber @GargDivanshu ! I'm planning to start working on it very soon, I'll tag this issue once I've opened a PR for it, if you want to have a...

Hey all! Implementation is well underway, and I'll open a PR in a couple of days for it (the entire Hugging Face team is currently at an off-site). Most likely,...

Hi again! The GOT-OCR PR is live [here](https://github.com/huggingface/transformers/pull/34721) if you want to follow the progress :)

GOT-OCR is now merged in the main branch of Transformers 🤗

Hello @aselimc , @dchou1618 and @vasanthrpjan1-boop ! Thanks for opening this issue @aselimc . Indeed sam3 doesn't support finetuning/doesn't have a loss out-of-the-box in transformers at the moment. However, seeing...