MonkeyOCRv2 is a visual-text foundation model for Document AI that provides document-native vision encoders, parsing models, and understanding models, achieving top performance on multilingual document parsing and recognition benchmarks.
336
No data
39
0
NOASSERTION
2026-07-28
It ranks #1 among open-source models on the MDPBench multilingual document parsing leaderboard with 83.3 overall, and releases the largest open-source document pre-training dataset (MonkeyDoc v2) with 113M images across 17 languages, while offering a family of efficient models (S/B/AS) and vLLM integration with DFlash for 2× faster inference.
MonkeyOCRv2 Vision Encoder — A Document-Native Visual Backbone
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.