Dharma Field Extractor: Any Document In, Structured Fields in JSON Out
Specialized small vision-language models provide developers with efficient options for document processing and structured data extraction.
Reported by Hugging Face ·
What happened
A Hugging Face blog post introduces Dharma Field Extractor, a 4-billion-parameter image-text-to-text model designed to extract structured JSON fields from documents. The post also references related datasets and a DharmaOCR Lite demo Space for extracting text and tables from document images.
Who it’s about
- Dharma-AI
- Dharma Field Extractor
- DharmaOCR Lite
- Hugging Face
Source
More on models
Get a brief picked for you
Sign in to follow topics and companies, save stories and search the archive.
Sign in