openbmb/MiniCPM-OCR-Jev
image-text-to-text model by openbmb
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
GitHub · Free API · Usage · Skill MiniCPM-OCR Jev is a 2B OCR correctness decision model for text, formula, and table regions. Given a region image and a candidate OCR result, it returns a score from 0 to 1 — higher means the candidate is more likely correct. Use it to auto-accept reliable regions, route the rest to human review, or pick the best result among several OCR models. JevOCRBench is 93.6, above JEV-35B-A3B (90.1) and close to Qwen3.5-397B-A17B (93.8). Xiaomi-OCR-0, AUROC (×100) stays in 91.9–93.4. Trained from Qwen3.5-2B. The vision encoder and language backbone are retained, and the language-model output head lmhead is replaced with a binary classification head that learns whether a candidate is correct. Internally, the model uses a matched original region image, candidate text, and rendered image. When calling the cloud API, the Docker image, or the SDK service with a built-in renderer, provide the…
Read the full model card ↗ · Preview checked 2026-10-30T09:32:36.236Z
Inside the original model card — Document outline
- Architecture
- Inputs and outputs
- Evaluation Results
- Discrimination across OCR models
- Automatic screening to reduce human review
- Selecting across models to improve parsing quality
- Examples
- Quick start
- Fine-tuning
- Related checkpoints
- FAQ
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
openbmb/MiniCPM-OCR-Jev is a image-text-to-text model repository published by openbmb on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- Not reported
- Recent downloads (30 days)
- 1,770
- Cumulative likes
- 81
- Hugging Face trending score
- 81
- Reported safetensors parameters
- 2,213,245,760
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-23T09:19:17.000Z
- Last modified
- 2026-10-30T02:16:51.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: Qwen/Qwen3.5-2B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:49:30.141Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.