# Fine Tune text generation Model using different type of data

**URL:** <https://discuss.huggingface.co/t/fine-tune-text-generation-model-using-different-type-of-data/48923>\
**Category:** 🤗Transformers\
**Created:** [August 1, 2023, 6:51am UTC](https://discuss.huggingface.co/t/fine-tune-text-generation-model-using-different-type-of-data/48923 "2023-08-01T06:51:47Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Pranavagrl](https://avatars.discourse-cdn.com/v4/letter/p/73ab20/32.png) [@Pranavagrl](https://discuss.huggingface.co/u/Pranavagrl)\
**Post date:** [August 1, 2023, 6:51am UTC](https://discuss.huggingface.co/t/fine-tune-text-generation-model-using-different-type-of-data/48923/1 "2023-08-01T06:51:47Z")

</div>

Hi, I want to fine-tune a model for Text generation purposes using multiple datasets, i.e.  
Suppose i have a dataset

- sciq
- metaeval/ScienceQA\_text\_only
- GAIR/lima
- Open-Orca/OpenOrca
- openbookqa  
and I want to train my model using all this data, so I am not able to figure out how to do the preprocessing part. and train my model using multiple datasets.