How to use the BLT model and attach it to some existing transformer?

Hello,

I have a BLT model trained, but I am not sure how to use it. Since providing a sentence as input, it gives as otuput.
So not sure how to use this tokenizer free approach in a LM?
Please help here by providing some arch?

Thanks!

The issue names no files, tests, or entry points. Start by locating the BLT model usage examples and any documentation about connecting it to an existing transformer; done means providing a clear, repository-supported usage path and architecture example.

Written by the indexing model from the issue text.