# Multi-instance transformers

**URL:** <https://discuss.huggingface.co/t/multi-instance-transformers/23659>\
**Category:** 🤗Transformers\
**Created:** [September 27, 2022, 7:15am UTC](https://discuss.huggingface.co/t/multi-instance-transformers/23659 "2022-09-27T07:15:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![GuillemGSubies](https://avatars.discourse-cdn.com/v4/letter/g/e56c9b/32.png) [@GuillemGSubies](https://discuss.huggingface.co/u/GuillemGSubies)\
**Post date:** [September 27, 2022, 7:15am UTC](https://discuss.huggingface.co/t/multi-instance-transformers/23659/1 "2022-09-27T07:15:26Z")

</div>

Hello!

I have a dataset where each sample is composed of n texts (the sum of their lengths in tokens is always greater than 512) and I would like to know if someone know what approach could I take to face this problem. It is a classification problem.

Thank you very much