Dharma-AI releases 2B-parameter model that extracts document fields as JSON
Dharma-AI has released the Dharma Field Extractor, a 2-billion-parameter model that takes a document image and returns structured, typed JSON instead of raw text. Two request modes are supported: an open mode that identifies fields from layout and context, and a schema-directed mode that returns exactly the key names and types supplied, using null where a requested field is absent. On the team's 546-document benchmark it scored 0.834 field-level F1, above the four frontier configurations they tested, while running self-hosted on a single L40S.
Why it matters
Teams pulling invoice, requisition or ID data can self-host a small model instead of paying per-token frontier API rates, and get JSON that already matches their downstream schema. Dharma-AI reports a 6x to 147x lower cost per extraction, though it notes self-hosted cost depends on hardware, volume and latency.
Sources
- PrimaryHugging Face
Written by AIToolMaps from the source above and checked against it sentence by sentence.