Datalab releases Lift, 9B open-weights vision model for structured JSON extraction from…

MarkTechPost

Lift is a 9B-parameter open-weights vision model that extracts structured JSON from PDFs and images using user-provided JSON schemas. It is Datalab's first model built purely for extraction, reading documents directly and decoding against the schema.

datalablift

MarkTechPost·Asif Razzaq

3 hours ago