# Can we fine-tune T5 for multiple tasks?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcan-we-fine-tune-t5-for-multiple-tasks%2F30268%3E%5C
**Category:** 🤗Transformers\
**Created:** [January 24, 2023, 6:40am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcan-we-fine-tune-t5-for-multiple-tasks%2F30268 "2023-01-24T06:40:12Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![viswanath660](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/viswanath660/32/13152_2.png) [@viswanath660](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fviswanath660)%5C
**Post date:** [January 24, 2023, 6:40am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcan-we-fine-tune-t5-for-multiple-tasks%2F30268%2F1 "2023-01-24T06:40:12Z")

</div>

I am fine-tuning T5 for multiple tasks so that they work together. I want the models to work together. For example, summarization and translation should work together. The summarized text is the input to the translation model and gets translated.

Q1. Can we train T5 with different datasets and prefixes and expect it to work this way?

Q2. Is it possible to concatenate the models and make them one single model?