# Creating Own model for custom data

**URL:** <https://discuss.huggingface.co/t/creating-own-model-for-custom-data/115783>\
**Category:** Beginners\
**Created:** [November 5, 2024, 8:31am UTC](https://discuss.huggingface.co/t/creating-own-model-for-custom-data/115783 "2024-11-05T08:31:13Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![kishanthan97](https://avatars.discourse-cdn.com/v4/letter/k/22d042/32.png) [@kishanthan97](https://discuss.huggingface.co/u/kishanthan97)\
**Post date:** [November 5, 2024, 8:31am UTC](https://discuss.huggingface.co/t/creating-own-model-for-custom-data/115783/1 "2024-11-05T08:31:13Z")

</div>

I need train the model for my own domain. The data format is text and I can insert it has pdf. Is there any guideline to do that. I trained some model using internet. But they are not giving good result. Simply I need to create a bot that is specific for my own domain. This is for learning purpose. So, I need open source

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [November 5, 2024, 9:00am UTC](https://discuss.huggingface.co/t/creating-own-model-for-custom-data/115783/2 "2024-11-05T09:00:57Z")

</div>

Could it be a case similar to these?

> [@Fine tune LLMs on PDF Documents](https://discuss.huggingface.co/t/fine-tune-llms-on-pdf-documents/71374):
>
> We are currently seeking assistance in fine-tuning the Mistral model using approximately 48 PDF documents. Specifically, our challenge lies in training the model using peft and preparing the documents for optimal fine-tuning. We are facing difficulties in locating suitable resources for this task, and we are also uncertain about the proper procedures for document preparation, storage, and supply. If anyone within the community has expertise in this area or can provide guidance on the aforementi…

> [@Training a model for a PDF with OCR - where to begin?](https://discuss.huggingface.co/t/training-a-model-for-a-pdf-with-ocr-where-to-begin/40616):
>
> Total newbie here when it comes to ML etc. I have a pdf with pages that look like this which I can export to jpegs: I want to train my model to be able to get the: Question number The question linked to the number The number of marks linked to that question Any diagrams linked to the question Any answer spaces linked to the question I’m having a go at using Label Studio to label the areas. Then train with Tensorflow? Is this correct first steps? Once I labelled them, how do I …