GeoLayoutLM: Warning about mismatched tokenizer class: BrosTokenizer vs BertTokenizer

[vodatvan01]

Hi, I encountered this warning when running the code:

The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'BertTokenizer'.
The class this function is called from is 'BrosTokenizer'.

However, in the code I only see this line:

TOKENIZER = BertTokenizer.from_pretrained("bert-large-uncased", do_lower_case=True)

I couldn't find any BrosTokenizer in the codebase. Is this warning expected, or could there be a mismatch somewhere in how the tokenizer is being used or loaded?

Thanks!

[Ashu7788-alt]

bert-large-uncased

You can download the bert-large-uncased model to your local machine and then update the code to point to your local path.