AITOPAI热报
ModelsSelected

面壁智能开源 MiniCPM-OCR 套件，1B 模型主打轻量快速解析

官方账号面壁智能 ModelBest@ModelBest_AI
Post
View the post
Why we picked it

面壁开源了一套 OCR 套件，1B 模型负责解析，2B 模型负责查错，最高每分钟 128 页，还支持 vLLM 和 Ollama，本地跑文档识别可以试试。

面壁智能（ModelBest）发布开源 OCR 套件 MiniCPM-OCR，包含两个模型。MiniCPM-OCR 1.0 是 1B 参数的 OCR 模型，定位小体量下的高精度快速解析；MiniCPM-OCR Jev 是 2B 的决策模型，用于校验不同 OCR 解析器输出的文本、公式和表格准确性。配合 SDK 并发优化，吞吐最高可达每分钟 128 页，套件支持 vLLM、SGLang、llama.cpp 和 Ollama，并提供量化模型、微调支持和 Agent Skills。

Image · 面壁智能 ModelBest
Original · 面壁智能 ModelBest

Introducing the MiniCPM-OCR suite 🚀 An open-source OCR suite for fast parsing and correctness assessment. 🔹 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale. Compact, accurate, and fast. 🔹 MiniCPM-OCR Jev — a 2B decision model that helps assess parsing accuracy by checking text, formulas, and tables from different OCR parsers. With SDK concurrency optimizations, throughput can reach up to 128 pages per minute. The suite supports vLLM, SGLang, llama.cpp, and Ollama, with quantized models, fine-tuning support, and Agent Skills. Ready to put MiniCPM-OCR to work? 👇

🔗 GitHub： https://t.co/pBrKdR3ZUp 🤗 Hugging Face: MiniCPM-OCR 1.0：https://t.co/LazdAUhxal MiniCPM-OCR Jev：https://t.co/EivMYVMj80 👉 Try the Demo：https://t.co/HMgTnDfwCo Use the API：https://t.co/ZQ8Dsf079g

#MiniCPM-OCR#面壁智能#开源模型#多模态#OCR

Keep reading

Recent stories with the same tag or section
ModelsBuildersSelected03:58
OpenBMB releases MiniCPM-OCR 1.0, a 1.3B open-source OCR model

A 1.3B model running on llama.cpp or Ollama means document OCR can now run locally on modest hardware instead of paying per-page on hyperscaler APIs, with the bundled 2B judge model solving the practical problem of knowing when OCR output needs human review. Teams processing Chinese- and English-heavy document pipelines should benchmark it against PaddleOCR-VL-1.6 on their own pages. Weights are on Hugging Face and GitHub.

#MiniCPM-OCR#OpenBMB#open-source models#OCR
Aran Komatsuzaki (论文推介)@arankomatsuzakiSource
ModelsBuildersMulti-sourceSelected00:53
MiniCPM-OCR 1.0 and Jev: open-source OCR parsing and verification models

The pairing of a small parser with a separate verification model is the notable design choice: Jev is model-agnostic, so teams can keep their existing OCR engine and add quality checking without swapping stacks. Developers processing documents at volume can benchmark it against PaddleOCR-VL-1.6 or MinerU2.5 Pro using the released GitHub code, Hugging Face weights, and hosted API. The day-0 support across 12 chip vendors also eases deployment on non-NVIDIA hardware.

#MiniCPM-OCR#OpenBMB#OCR#open-source models
Event
OpenBMB@OpenBMB3 sourcesSource