# Auth problem when using fine tuned model

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fauth-problem-when-using-fine-tuned-model%2F28037%3E%5C
**Category:** Beginners\
**Created:** [December 17, 2022, 7:36pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fauth-problem-when-using-fine-tuned-model%2F28037 "2022-12-17T19:36:04Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![MokaExpress](https://avatars.discourse-cdn.com/v4/letter/m/9d8465/32.png) [@MokaExpress](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMokaExpress)%5C
**Post date:** [December 17, 2022, 7:36pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fauth-problem-when-using-fine-tuned-model%2F28037%2F1 "2022-12-17T19:36:04Z")

</div>

Hi there,  
I am a beginner to ML and doing uni project, facing deadline tomorrow.  
I successfully fine tuned a pre trained model, pushed to hub. Now it is about using it for predictions. There I got stuck.  
My repository xx/yy is public.

pred\_pipeline = pipeline(model=“xx/yy”)

OSError: xx/yy is not a local folder and is not a valid model identifier listed on ‘[Models - Hugging Face](https://huggingface.co/models)’  
If this is a private repository, make sure to pass a token having permission to this repo with `use_auth_token` or log in with `huggingface-cli login` and pass `use_auth_token=True`.

I did the following  
!huggingface-cli login  
Entered my token  
Change the code as below  
pred\_pipeline = pipeline(model=“xx/yy”, use\_auth\_token=True)

It didnt work.  
I seriously don’t know how to make it work. Cannot believe I am failing in the last step… Can anyone pls help me? Your help is highly appreciated

Regards, Shanshan