Public KG record
DharmaOCR-LITE v1.1
Recorded overview
A 2-billion-parameter base model optimized for OCR through supervised fine-tunin
Extract text from images, scans, or PDFs while preserving layout, tables, and document structure.
Recorded details
- Capabilities: OCR across a wide range of documents including contracts, court filings, invoices, IDs, and forms
- Capabilities: specialized for OCR through supervised fine-tuning and DPO
- Requirements: 2-billion-parameter base model
Evidence coverage
The KG currently records 7 known information dimensions and has 11 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Dharma Field Extractor — based on