# Multi-class classification and Hosted inference API

**URL:** <https://discuss.huggingface.co/t/multi-class-classification-and-hosted-inference-api/11123>\
**Category:** 🤗Hub\
**Created:** [October 27, 2021, 1:31pm UTC](https://discuss.huggingface.co/t/multi-class-classification-and-hosted-inference-api/11123 "2021-10-27T13:31:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![maxpower](https://avatars.discourse-cdn.com/v4/letter/m/839c29/32.png) [@maxpower](https://discuss.huggingface.co/u/maxpower)\
**Post date:** [October 27, 2021, 1:31pm UTC](https://discuss.huggingface.co/t/multi-class-classification-and-hosted-inference-api/11123/1 "2021-10-27T13:31:26Z")

</div>

Hi all,

I want to publish a multi-class text classification model (emotion detection). Currently, the probabilities for all classes sum up to 1. But each class should handled independently from the others (e.g., anger 0.6, joy 0.7, etc…)

What parameters are necessary for the YAML section in der model card?

[Here my model.](https://huggingface.co/maxpower/my-awesome-model)

Thanks,  
Max