paperless-ngx?

This t5 is multimodal.

Also a hint: you can create a finetuning dataset from a frontier LLM pretty easily to finetune those t5 and effectively distill them pretty fast these days

In general encoder+decoder models are much more efficient at infererence than decoder-only models because they run over the entire input all at once (which leverages parallel compute more effectively).

The issue is that they're generally harder to train (need input/output pairs as a training dataset) and don't naturally generalize as well

Encoder/decoder is much, much more efficient for finetuning and inference than decoder-only models.

Historically T5 are good when you finetune them for task specific models (translation, summarization, etc).