# Finetune LayoutLM for multilabel document image classification

**URL:** <https://discuss.huggingface.co/t/finetune-layoutlm-for-multilabel-document-image-classification/47167>\
**Category:** Models\
**Created:** [July 18, 2023, 8:39am UTC](https://discuss.huggingface.co/t/finetune-layoutlm-for-multilabel-document-image-classification/47167 "2023-07-18T08:39:43Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![LaFlowBy](https://avatars.discourse-cdn.com/v4/letter/l/87869e/32.png) [@LaFlowBy](https://discuss.huggingface.co/u/LaFlowBy)\
**Post date:** [July 18, 2023, 8:39am UTC](https://discuss.huggingface.co/t/finetune-layoutlm-for-multilabel-document-image-classification/47167/1 "2023-07-18T08:39:43Z")

</div>

Hey,

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](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/LayoutLMv2/RVL-CDIP/Fine_tuning_LayoutLMv2ForSequenceClassification_on_RVL_CDIP.ipynb)

Any assistance would be greatly appreciated.