Dharma-AI released a 2-billion-parameter Field Extractor model that outputs structured JSON directly from document images.
Dharma-AI has launched the Dharma Field Extractor on Hugging Face. It features a 2-billion-parameter model trained with a LoRA adapter (43,384 samples) derived from DharmaOCR-LITE v1.1. The tool supports both open and schema-based request methods, converting document images into structured JSON with type annotations. Missing fields are returned as null.
Continue looking at this topic
Direct useDocument Format Conversion ↗Open-source projectDocument OCR recognized the characters correctly but scrambled the reading order: how to choose tools like indra? ↗Related contentWhat is Qwen-VL? How does image and video understanding differ from image generation ↗OpportunitiesFound a product recommendation | 473 followers, PDF editing tool sold 594 copies ↗Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original