NielsRogge
NielsRogge
Hi @venkat-natchi, would it be possible to rebase your branch on the main branch of transformers? This way, the CI becomes greener, and allows us to review the PR in...
Yeah I marked this as good first issue as someone could take a deeper dive into DETR's position embeddings. Reading the [paper](https://arxiv.org/abs/2005.12872) for that could definitely be helpful. But the...
cc'ing @Narsil for enabling the model on the inference API, cc'ing @stevhliu for adding tutorial documentation to the task summary
To create a LayoutXLM-large, you can copy paste the weights from [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) into the model. You can do that by converting the weights as done in any conversion script, like...
@philmas the best way is to combine LiLT with a Dutch roberta-base model. For Dutch, the best roberta-base model is currently this one: https://huggingface.co/DTAI-KULeuven/robbert-2023-dutch-base. Hence please follow this guide to...
Usuallly I recommend starting with 100, but as always with deep learning, the more the better
Hi, Could you clarify what you mean by multiclass? SAM just takes an image and prompt as input, and generates a mask for it. So if you want to generate...
Hi, See #259 for easy inference with DPT + Swin backbone
Error Loading Pre-trained Weights: Size Mismatch in DPTDepthModel when trying to run for first time.
For easy inference see #259