Unused variable `q_embed` in the Llama's `preprocess_query` method

[seunghyukoh]

Hi, while reviewing the UnlimiformerLLaMa class, I found an unused variable in the preprocess_query method.

The variable q_embed looks quite important since it's related to Llama's rotary embedding. Is this intentional?

Thanks!

[urialon]

Hi @jake-seunghyukoh ,
Thank you for your interest in our work and for reporting this!

This unused variable practically lead the model to use position==0 for the query.
This was fixed in 60b4316

Thanks again, let us know if you have any more questions!

Best,
Uri