01

Basic information

Model repository: isLinXu/WeVisOne-VL-2B
Organization: isLinXu
Tasks: image-text-to-text

02

Architecture and runtime

Model type: qwen3_vl
Architecture: Qwen3VLForConditionalGeneration
Libraries: safetensors, pytorch
Base models:
Current revision: master

03

License and update history

License: apache-2.0
Created: 2026-10-24
Last updated: 2026-10-24

vision-languageqwen3_vlobject-detectionreferring-expression-comprehensionobject-countingpoint-groundingocrreferring-expression-segmentationimage-matting
04

Hardware requirements

Not filled in locally.

05

Download links

Not filled in locally.

06

Basic usage example

Not filled in locally.