# Give 2 inputs to BERT

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgive-2-inputs-to-bert%2F23997%3E%5C
**Category:** 🤗Transformers\
**Created:** [October 4, 2022, 2:59pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgive-2-inputs-to-bert%2F23997 "2022-10-04T14:59:42Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![valeriova96](https://avatars.discourse-cdn.com/v4/letter/v/d78d45/32.png) [@valeriova96](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fvaleriova96)%5C
**Post date:** [October 4, 2022, 2:59pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgive-2-inputs-to-bert%2F23997%2F1 "2022-10-04T14:59:42Z")

</div>

I need to evaluate the following: Pr(y | x\_i, k) forall i, where x\_is are elements from my dataset (i.e. text sentences) and k is another set of sentences extracted from a document that I’d like to compare my input to. Is it possible to do so?  
Consider size(X) == size(k), hence I cannot put both into a dataloader, plus I’d like to have whole k evaluated against each x\_i element.  
Thanks in advance to y’all 🙂