FrontierThe story, in brief
Datalab Releases lift: A 9B Open-Weights Vision Model That Extracts Structured JSON From PDFs Using Schemas
90.2% field accuracy. Datalab's 9B vision model turns PDFs into valid JSON without hallucination—and it's open-weights.
The KeyNews take
Why it matters
A practical, production-ready vision model for document automation that solves a real enterprise pain point (PDF-to-structured-data) with schema constraints and trained abstention. Open-weights release makes it immediately deployable.
The key facts
8 to knowModel size: 9B parameters
Open-weights release
90.2% field accuracy on 225-document benchmark
Schema-constrained decoding for output validity
Trained abstention to avoid hallucinations on missing fields
Converts PDFs and images to schema-matching JSON
Released by Datalab
Published June 23, 2026
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: Datalab released lift, a 9B open-weights vision model that turns PDFs and images into schema-matching JSON. It uses schema-constrained decoding for valid structure and trained abstention to return null instead of hallucinating absent fields, scoring 90.2% field accuracy on a 225-document benchmark.