# Returning Multiple Questions for a Question Generation Model on SageMaker

**URL:** <https://discuss.huggingface.co/t/returning-multiple-questions-for-a-question-generation-model-on-sagemaker/29816>\
**Category:** Amazon SageMaker\
**Created:** [January 16, 2023, 4:42pm UTC](https://discuss.huggingface.co/t/returning-multiple-questions-for-a-question-generation-model-on-sagemaker/29816 "2023-01-16T16:42:32Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![artificial-wizard](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/artificial-wizard/32/13632_2.png) [@artificial-wizard](https://discuss.huggingface.co/u/artificial-wizard)\
**Post date:** [January 16, 2023, 4:42pm UTC](https://discuss.huggingface.co/t/returning-multiple-questions-for-a-question-generation-model-on-sagemaker/29816/1 "2023-01-16T16:42:32Z")

</div>

Hi,

I am using valhalla/t5-base-qa-qg-hl([valhalla/t5-base-qa-qg-hl · Hugging Face](https://huggingface.co/valhalla/t5-base-qa-qg-hl)) Text2Text-Generation Model to generate questions from some context. When it comes to inference, I have found that on sagemaker it is only returning one output, while running the model locally the model generates multiple output.

I wanted to get all the model outputs from sagemaker endpoint. I am using the sagemaker api to deploy it there.

Thanks,  
Jatin
