yeah, there are models for that already, some are interesting, some are not. check out PEXEL and DeepSeek-OCR. in theory this could cut costs pretty well for long contexts + there no tokenisation layer.
yeah, there are models for that already, some are interesting, some are not. check out PEXEL and DeepSeek-OCR. in theory this could cut costs pretty well for long contexts + there no tokenisation layer.