# Fine tuning using llm Qlora

**URL:** <https://discuss.huggingface.co/t/fine-tuning-using-llm-qlora/78334>\
**Category:** Beginners\
**Created:** [March 20, 2024, 8:28pm UTC](https://discuss.huggingface.co/t/fine-tuning-using-llm-qlora/78334 "2024-03-20T20:28:03Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![pravingaikwad549](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/pravingaikwad549/32/24989_2.png) [@pravingaikwad549](https://discuss.huggingface.co/u/pravingaikwad549)\
**Post date:** [March 20, 2024, 8:28pm UTC](https://discuss.huggingface.co/t/fine-tuning-using-llm-qlora/78334/1 "2024-03-20T20:28:04Z")

</div>

I am trying to fine tune T5 for question and answering task using Qlora. But I think I am doing something incorrect as the time and space taken by the qlora model is same while fine tuning the full model.  
I have imported the model using the bnbconfig and added lora to it using loraconfig, (the model.print\_trainable\_parameter gives 0.08 % trainable parameters).  
How do I check if only the lora parameters are getting updated?