# Train a model on a specific Document

**URL:** <https://discuss.huggingface.co/t/train-a-model-on-a-specific-document/21936>\
**Category:** Beginners\
**Created:** [August 22, 2022, 8:38pm UTC](https://discuss.huggingface.co/t/train-a-model-on-a-specific-document/21936 "2022-08-22T20:38:54Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![kabalanresearch](https://avatars.discourse-cdn.com/v4/letter/k/e68b1a/32.png) [@kabalanresearch](https://discuss.huggingface.co/u/kabalanresearch)\
**Post date:** [August 22, 2022, 8:38pm UTC](https://discuss.huggingface.co/t/train-a-model-on-a-specific-document/21936/1 "2022-08-22T20:38:54Z")

</div>

Is it possible to train (fine tune) a model like gpt-j on a specific document so it is familiar with its content ?

---

<div class="post-metadata">

**Author:** ![dato3000](https://avatars.discourse-cdn.com/v4/letter/d/b5e925/32.png) [@dato3000](https://discuss.huggingface.co/u/dato3000)\
**Post date:** [February 18, 2023, 4:43pm UTC](https://discuss.huggingface.co/t/train-a-model-on-a-specific-document/21936/2 "2023-02-18T16:43:52Z")

</div>

did you ever find out?