# Unusual input\_id size for distilBERT tokenizer

**URL:** <https://discuss.huggingface.co/t/unusual-input-id-size-for-distilbert-tokenizer/86695>\
**Category:** 🤗Tokenizers\
**Created:** [May 14, 2024, 5:29pm UTC](https://discuss.huggingface.co/t/unusual-input-id-size-for-distilbert-tokenizer/86695 "2024-05-14T17:29:07Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rishuhuhu](https://avatars.discourse-cdn.com/v4/letter/r/3ab097/32.png) [@rishuhuhu](https://discuss.huggingface.co/u/rishuhuhu)\
**Post date:** [May 14, 2024, 5:29pm UTC](https://discuss.huggingface.co/t/unusual-input-id-size-for-distilbert-tokenizer/86695/1 "2024-05-14T17:29:07Z")

</div>

I am tokenizing a news article using DistilBERT tokenizer whose max token length supposed to be 512, but I a getting 280,

 ![Screenshot 2024-05-14 225447](https://us1.discourse-cdn.com/hellohellohello/original/3X/3/2/3264fee9434509089a8709a42be82a510d262d2f.png)

I dont know what is the issue, I have worked with DistilBERT before and it used to give 512 as the max length…