Finetune LayoutLM for multilabel document image classification


i am trying to finetune a LayoutLMv2ForSequenceClassification model for document image classification (with multilabel).

I read that the pre-training of the model was partly done with Multi-label Document Classification

Is it possible to do that for finetuning too?
I only found examples for exclusive classes: e.g. here

Any assistance would be greatly appreciated.