NielsRogge

I haven't tried the pipeline yet with various thresholds. Do you think we should lower it even more? It could result in too many detections. Wondering what the best default...

Ok thanks, will merge in that case.

Hi, I think Swin Transformer already works on any resolution.

@the-neural-networker I checked it, so currently any height and width are supported if divisible by 32. I assume you can continue with supporting interpolation of position embeddings, since that would...

I had the same error and fixed it by using `model.config.use_cache=False` during training. But @VictorSanh might know a better option

Yes this is due to batches having different lengths of `input_ids` (in the code snippet of your first message, you set `padding=True` which means dynamic padding, each batch may have...

Hi @EloiEynard I just uploaded an example notebook for fine-tuning Idefics2 on an image -> JSON dataset here: https://github.com/NielsRogge/Transformers-Tutorials/blob/master/Idefics2/Fine_tune_Idefics2_for_JSON_extraction_use_cases_(PyTorch_Lightning).ipynb

I had the same question, turns out both are equivalent. The `get_peft_model` API is recommended as it returns a `PeftModel` which has additionally utility methods such as `save_adapter()` with support...

It would be great to have a first round of review as the PR is in a ready state.

@EduardoPach feel free to comment on the PR what you'd change. @Namangarg110 haven't had time to review your PR yet, will do so this week.