Dharma Field Extractor: Any Document In, Structured Fields in JSON Out
3.60T1.5 sourceHugging Face Blog
Source record
Published by Hugging Face Blog (T1.5 source). The original is at https://huggingface.co/blog/Dharma-AI/dharma-field-extractor.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryDharma-AI presents Dharma Field Extractor, a 2-billion-parameter model that converts contracts, invoices, forms, IDs, and other documents into requested JSON fields. The post reports better results than tested frontier LLMs at lower cost, extending the team’s earlier domain-specialized OCR model.
Why it mattersDocuments the model, supported use cases, and benchmark result, giving readers a concrete option for replacing manual field mapping and prompt-driven extraction.
Cited by
No citations on record.