PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text
•
1.0B
•
Updated
•
17.9k
•
1.43k
Document Understanding
https://www.2077ai.com/dataset/dataset-omnidocbench
Note Multi page support? Maybe with: "concatenate_markdown_pages"
opendatalab/MinerU2.5-2509-1.2B
Image-Text-to-Text • 1B • Updated • 1.06M • 302Note agpl-3.0 license: "If you use AGPL-3.0 licensed software in a network-accessible application, you must make the entire source code of your application available to users of that application." :(
-
rednote-hilab/dots.ocr
Image-Text-to-Text • 3B • Updated • 923k • 1.17k -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 4.37M • 3k