# Transformer for very big text

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftransformer-for-very-big-text%2F9864%3E%5C
**Category:** 🤗Transformers\
**Created:** [September 9, 2021, 6:57pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftransformer-for-very-big-text%2F9864 "2021-09-09T18:57:43Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Muhammad4hmed](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/muhammad4hmed/32/2682_2.png) [@Muhammad4hmed](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMuhammad4hmed)%5C
**Post date:** [September 9, 2021, 6:57pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftransformer-for-very-big-text%2F9864%2F1 "2021-09-09T18:57:43Z")

</div>

So I have some ~1200 data consisting of assembly language which has on average of ~15K words per line which is indeed very big data and I want to classify them into two classes (they are labelled)

Any method I can achieve my goal? as the transformers max length limit is mostly 256 or 512.

Thanks.

---

<div class="post-metadata">

**Author:** ![theTechie](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/thetechie/32/4681_2.png) [@theTechie](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FtheTechie)%5C
**Post date:** [May 6, 2022, 11:58am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftransformer-for-very-big-text%2F9864%2F2 "2022-05-06T11:58:14Z")

</div>

[Longformer](https://huggingface.co/docs/transformers/model_doc/longformer) might help you