# Fine tuning model for stack exchange

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-model-for-stack-exchange%2F15255%3E%5C
**Category:** Models\
**Created:** [March 2, 2022, 11:45am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-model-for-stack-exchange%2F15255 "2022-03-02T11:45:44Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Jamesmin90](https://avatars.discourse-cdn.com/v4/letter/j/edb3f5/32.png) [@Jamesmin90](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJamesmin90)%5C
**Post date:** [March 2, 2022, 11:45am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-model-for-stack-exchange%2F15255%2F1 "2022-03-02T11:45:44Z")

</div>

Hi everyone, I am trying to build a BERT model which takes stack exchange answers with it’s scores as training data to predict whether or not an answer is good or bad during the testing. Any idea how I would build this model or any useful articles which might help? The first problem I would like to solve is how not to use labels, but use scores. Thank you 😄