ModelBest OpenBMB Launches the MiniCPM-OCR Model Family, Including Two Models for Parsing and Reliability Assessment
ModelBest OpenBMB and ModelBest have launched the open-source model family MiniCPM-OCR, designed to convert documents into structured information. Among them, MiniCPM-OCR 1.0 is a 1.3B-parameter model that supports Chinese and English documents, can handle scanned pages, photographed documents, tilted and curved pages, and supports tables, formulas, PDFs, and key information extraction; the other model, MiniCPM-OCR Jev, is used to assess the reliability of OCR results and help identify outputs that require manual review. Both models have released their weights and offer multiple deployment methods.
Why read this
AI score 57
The original article places document parsing and OCR result reliability assessment within the same model family, so readers can understand how, after parsing, outputs requiring manual review are filtered out.
Topics
View original postDOCUMENT PARSING IS GETTING REALLY INTERESTING MiniCPM-OCR is an open-source model family from @OpenBMB and ModelBest built to turn documents into structured, usable information. → MiniCPM-OCR 1.0 is a compact 1.3B-parameter model for English and Chinese documents → handles scanned pages, photographed documents, tilted inputs and even curved pages → supports tables, formulas, PDFs and key information extraction → lets you inspect the Markdown source and preview the parsed output the family also includes MiniCPM-OCR Jev, a separate model that assesses the reliability of OCR results and helps identify outputs that may need human review. pretty cool to see document parsing and output assessment tackled together, with open-source weights and multiple deployment options. GitHub: https://t.co/7SPyXoTA2o Hugging Face: MiniCPM-OCR 1.0：https://t.co/07gayee7eY MiniCPM-OCR Jev：https://t.co/jn6LLkFNft
View original
DOCUMENT PARSING IS GETTING REALLY INTERESTING MiniCPM-OCR is an open-source model family from @OpenBMB and ModelBest built to turn documents into structured, usable information. → MiniCPM-OCR 1.0 is a compact 1.3B-parameter model for English and Chinese documents → handles scanned pages, photographed documents, tilted inputs and even curved pages → supports tables, formulas, PDFs and key information extraction → lets you inspect the Markdown source and preview the parsed output the family also includes MiniCPM-OCR Jev, a separate model that assesses the reliability of OCR results and helps identify outputs that may need human review. pretty cool to see document parsing and output assessment tackled together, with open-source weights and multiple deployment options. GitHub: https://t.co/7SPyXoTA2o Hugging Face: MiniCPM-OCR 1.0：https://t.co/07gayee7eY MiniCPM-OCR Jev：https://t.co/jn6LLkFNft
Body
📄 Parsing documents is only half the job. Knowing which outputs need a second look matters too. 🔍 MiniCPM-OCR pairs document parsing with OCR reliability assessment to help build more dependable workflows. Thanks @dravenip for the thoughtful overview! 🚀