Decision Models / MiniCPM-OCR Jev
OPEN
MiniCPM-OCR Jev
By OpenBMB · First Hugging Face upload: 23 Oct 2026
This 2B specialist scores whether a candidate OCR reading matches a document region. It handles text, formulas and tables, returning a score from 0 to 1. Qwen3.5-2B supplies the backbone; a binary classification head replaces its language head. Scores can help select among OCR engines or route uncertain regions to a person.
Facts
- Size
- 2B
- Base
- Qwen3.5-2B
- Licence
- Apache-2.0
- Access
- Open weights in BF16, AWQ, GPTQ and GGUF; a free API on ModelBest's platform
Claims and sources
- OpenBMB reports decision AUROC ×100 of 93.6 on its JevOCRBench, against 90.1 for a row named JEV-35B-A3B and 93.8 for Qwen3.5-397B-A17B. The card does not identify JEV-35B-A3B further. vendor reportedsource
- Across four OCR parsers on the same 200 samples with manually labelled readings, OpenBMB reports AUROC ×100 from 91.9 to 93.4. These are its own parser and sample combinations. vendor reportedsource
Links
Source: Weights and model card → Source: Code and deployment → Source: JevOCRBench → Source: Hugging Face upload metadata →
Related projects
No related projects are listed in the registry.