# Finetune GPT-J on custom dataset

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-gpt-j-on-custom-dataset%2F13832%3E%5C
**Category:** Models\
**Created:** [January 18, 2022, 7:00am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-gpt-j-on-custom-dataset%2F13832 "2022-01-18T07:00:32Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![theainerd](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/theainerd/32/38982_2.png) [@theainerd](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftheainerd)%5C
**Post date:** [January 18, 2022, 7:00am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-gpt-j-on-custom-dataset%2F13832%2F1 "2022-01-18T07:00:32Z")

</div>

Hello Community,

First of all thanks for the amazing blog regarding how to deploy GPTJ in production.  
I want to go a step further and fine tune a model using GPTJ for my specific use case.

Is there any way i can do it using Hugging face? Any help would be great.

Some helful links:

- [GitHub - mallorbc/Finetune\_GPTNEO\_GPTJ6B: Repo for fine-tuning GPTJ and other GPT models](https://github.com/mallorbc/Finetune_GPTNEO_GPTJ6B)
