# Does tokenizer.max\_model\_input\_sizes do anything?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdoes-tokenizer-max-model-input-sizes-do-anything%2F6440%3E%5C
**Category:** 🤗Transformers\
**Created:** [May 28, 2021, 6:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdoes-tokenizer-max-model-input-sizes-do-anything%2F6440 "2021-05-28T06:49:42Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![normster](https://avatars.discourse-cdn.com/v4/letter/n/2bfe46/32.png) [@normster](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnormster)%5C
**Post date:** [May 28, 2021, 6:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdoes-tokenizer-max-model-input-sizes-do-anything%2F6440%2F1 "2021-05-28T06:49:42Z")

</div>

Hi,

Is the `max_model_input_sizes` [field on a tokenizer](https://github.com/huggingface/transformers/blob/master/src/transformers/models/clip/tokenization_clip.py#L141) used anywhere, and how does it interact with the `max_position_embeddings` [field on a model](https://github.com/huggingface/transformers/blob/master/src/transformers/models/clip/configuration_clip.py#L96)? I don’t see any usages of this field outside of a research script.

Thanks,  
Norman