# Is there a way to get the logits as output in zero shot classification Pipeline?

**URL:** <https://discuss.huggingface.co/t/is-there-a-way-to-get-the-logits-as-output-in-zero-shot-classification-pipeline/8824>\
**Category:** 🤗Transformers\
**Created:** [July 30, 2021, 3:58am UTC](https://discuss.huggingface.co/t/is-there-a-way-to-get-the-logits-as-output-in-zero-shot-classification-pipeline/8824 "2021-07-30T03:58:43Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![akar5h](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/akar5h/32/2177_2.png) [@akar5h](https://discuss.huggingface.co/u/akar5h)\
**Post date:** [July 30, 2021, 3:58am UTC](https://discuss.huggingface.co/t/is-there-a-way-to-get-the-logits-as-output-in-zero-shot-classification-pipeline/8824/1 "2021-07-30T03:58:43Z")

</div>

Hi, I was wondering if it was possible to get the output logits ( the model output : model(input)) as an output along with the multi-class label dict in zero-shot classification pipeline?  
I want to use the logit probabilities to make some other inferences.