# Finetuned model outputs verbosity

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuned-model-outputs-verbosity%2F76481%3E%5C
**Category:** Beginners\
**Created:** [March 8, 2024, 4:13am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuned-model-outputs-verbosity%2F76481 "2024-03-08T04:13:19Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![nksk](https://avatars.discourse-cdn.com/v4/letter/n/258eb7/32.png) [@nksk](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnksk)%5C
**Post date:** [March 8, 2024, 4:13am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuned-model-outputs-verbosity%2F76481%2F1 "2024-03-08T04:13:19Z")

</div>

Hi all, I finetuned Mistral 7B base model for a specific application. I get great results, but after outputting the required result, the model continues with some additional sentences I don’t need. How should I prevent it so that it behaves like instruction model?