01

Basic information

Model repository: ATH-MaaS/OvisOCR2
Organization: ATH-MaaS
Tasks: image-text-to-text

02

Architecture and runtime

Model type: qwen3_5
Architecture: Qwen3_5ForConditionalGeneration
Libraries: safetensors, pytorch
Base models: Qwen/Qwen3.5-0.8B
Current revision: master

03

License and update history

License: apache-2.0
Created: 2026-07-14
Last updated: 2026-08-29

ocrdocument-parsingmultimodalmarkdowntablesformulasvllmqwen3_5
04

Hardware requirements

Not filled in locally.

05

Download links

Not filled in locally.

06

Basic usage example

Not filled in locally.