面壁智能发布 MiniCPM-OCR 1.0 与校验模型 Jev
🎬 MiniCPM-OCR in action — running locally on iPhone Duo and iPad.
面壁智能发布 MiniCPM-OCR 1.0，这是一个 1B 规模的 OCR 模型，在 Real5-OmniDocBench 上取得 93.68、在 OCRBench v2 上取得 54.7。同时发布 2B 的决策模型 MiniCPM-OCR Jev，用于比对解析结果与原图并给出 0–1 正确性评分，在 JevOCRBench 上接近 Qwen3.5-397B-A17B。两个模型均开放权重，支持 llama.cpp、vLLM、SGLang、Ollama 部署，并提供开源微调代码。
推荐理由
AI 评分 60
面壁智能开源 1B 的 OCR 模型与 2B 的校验模型，并给出端侧本地运行与多种推理框架的部署方式。
主题
正文
🎬 MiniCPM-OCR in action — running locally on iPhone Duo and iPad. Parse fast and accurately. Guard the results. All in your hands. 🙌
Handwritten notes, complex formulas, newspapers, poor-quality scans—real documents put OCR to the test.
📄 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale. It achieves 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, combining accurate document parsing with efficient inference.
🛡️ MiniCPM-OCR Jev — A 2B decision model that checks OCR accuracy. It approaches Qwen3.5-397B-A17B on JevOCRBench and works with outputs from different OCR parsers.
Watch it compare parsed text, formulas, and tables with the original image and assign 0–1 correctness scores—helping you pick better results and identify what needs human review.
🔓 Open weights. Deploy your way. Run with llama.cpp, vLLM, SGLang, or Ollama. Customize with open-source fine-tuning code.
Watch it in action. 👇
🔗 GitHub: https://t.co/2SlATAJk08 🤗 Hugging Face: https://t.co/Ttq31GL8eJ 👉 Try the Demo：https://t.co/QsFAJT3AFy Use the API：https://t.co/dP01jBS2j2