# How to use question answering pretrained model

**URL:** <https://forum.rasa.com/t/how-to-use-question-answering-pretrained-model/40550>\
**Category:** Rasa Open Source\
**Created:** [February 24, 2021, 5:56am UTC](https://forum.rasa.com/t/how-to-use-question-answering-pretrained-model/40550 "2021-02-24T05:56:37Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![salmanhiro](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/salmanhiro/32/12750_2.png) [@salmanhiro](https://forum.rasa.com/u/salmanhiro)\
**Post date:** [February 24, 2021, 5:56am UTC](https://forum.rasa.com/t/how-to-use-question-answering-pretrained-model/40550/1 "2021-02-24T05:56:37Z")

</div>

Hi,

I wonder whether there is a chance to use some question-answering language model for general conversation (i.e [deepset/roberta-base-squad2 · Hugging Face](https://huggingface.co/deepset/roberta-base-squad2)) instead of feeding the conversation into NLU and domain (this will take forever to write them one by one 😅) and not only use the transformer for classification (i am not into giving the class), but also for response generation since what I want to build is not just a customer service chatbot or something similar but a personal assistant.

---

_[View the full topic](https://forum.rasa.com/t/how-to-use-question-answering-pretrained-model/40550)._