# Concatenate Sentances

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fconcatenate-sentances%2F4233%3E%5C
**Category:** Beginners\
**Created:** [March 8, 2021, 10:13am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fconcatenate-sentances%2F4233 "2021-03-08T10:13:08Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![david-waterworth](https://avatars.discourse-cdn.com/v4/letter/d/49beb7/32.png) [@david-waterworth](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdavid-waterworth)%5C
**Post date:** [March 8, 2021, 10:13am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fconcatenate-sentances%2F4233%2F1 "2021-03-08T10:13:09Z")

</div>

Is there a helper class somewhere in one of the huggingface libraries which can assist in the concatenation of multiple short sentences into a single tensor - I want to tokenise each input example, shuffle and then combine until they’re ~512 tokens long. I thought that was part of the RoBERTa training process but I could be mistaken.