# Extracting loras

**URL:** <https://discuss.huggingface.co/t/extracting-loras/58512>\
**Category:** Models\
**Created:** [October 13, 2023, 11:27pm UTC](https://discuss.huggingface.co/t/extracting-loras/58512 "2023-10-13T23:27:57Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![YaTharThShaRma999](https://avatars.discourse-cdn.com/v4/letter/y/41988e/32.png) [@YaTharThShaRma999](https://discuss.huggingface.co/u/YaTharThShaRma999)\
**Post date:** [October 13, 2023, 11:27pm UTC](https://discuss.huggingface.co/t/extracting-loras/58512/1 "2023-10-13T23:27:57Z")

</div>

Is there a way to extract Lora’s from models? There is a way to do this with stable diffusion models here [https://github.com/bmaltais/kohya\_ss/blob/master/networks/extract\_lora\_from\_models.py](https://github.com/bmaltais/kohya_ss/blob/master/networks/extract_lora_from_models.py)

But is there a way to do this with models like llama?