zenosai/MonkeyOCRv2-S
Image Feature Extraction • 28.5M • Updated • 160 • 6
MonkeyOCRv2
The collection of the paper `MonkeyOCRv2: A Visual-Text Foundation Model for Document AI`.
Note Vision encoder
-
zenosai/MonkeyOCRv2-B
Image Feature Extraction • 0.1B • Updated • 126 • 4 -
zenosai/MonkeyOCRv2-AS
Image Feature Extraction • 21M • Updated • 110 • 2
zenosai/MonkeyOCRv2-S-Parsing
Image-Text-to-Text • 0.8B • Updated • 179 • 2Note Document parsing model
-
zenosai/MonkeyOCRv2-B-Parsing
Image-Text-to-Text • 0.9B • Updated • 350 • 9
zenosai/MonkeyOCRv2-S-Und
Image-Text-to-Text • 2B • Updated • 106 • 2Note Document understanding model
-
zenosai/MonkeyOCRv2-B-Und
Image-Text-to-Text • 2B • Updated • 563 • 1 -
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI
Paper • 2607.11562 • Published • 75 -
zenosai/MonkeyDocv2
Updated • 51 • 2