# Funetune BART for text auto-encoder

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffunetune-bart-for-text-auto-encoder%2F26480%3E%5C
**Category:** Models\
**Created:** [November 22, 2022, 3:11am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffunetune-bart-for-text-auto-encoder%2F26480 "2022-11-22T03:11:58Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![bk073](https://avatars.discourse-cdn.com/v4/letter/b/8491ac/32.png) [@bk073](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbk073)%5C
**Post date:** [November 22, 2022, 3:11am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffunetune-bart-for-text-auto-encoder%2F26480%2F1 "2022-11-22T03:11:59Z")

</div>

Can I finetune BART based model for text auto-encoder task?

I want to pass a sentence to the encoder and learn representation and using that representation I want to generate the same text using decoder.

BART has been trained for this task, but how can I finetune this model ?
