# Training AutoModelForCausalLM in a Seq2Seq task

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftraining-automodelforcausallm-in-a-seq2seq-task%2F44484%3E%5C
**Category:** 🤗Transformers\
**Created:** [June 25, 2023, 2:00pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftraining-automodelforcausallm-in-a-seq2seq-task%2F44484 "2023-06-25T14:00:45Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![sd3ntato](https://avatars.discourse-cdn.com/v4/letter/s/838e76/32.png) [@sd3ntato](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsd3ntato)%5C
**Post date:** [June 25, 2023, 2:00pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftraining-automodelforcausallm-in-a-seq2seq-task%2F44484%2F1 "2023-06-25T14:00:45Z")

</div>

hello,  
I was wondering if there is any way to take a model from AutoModelForCausalLM and fine-tune it in a Seq2Seq task