PitVQA BBox Model (Deprecated)

Note: This is an earlier single-task model. For production use, see pitvqa-qwen2vl-unified-v2 which includes bbox detection plus more capabilities.

Description

Early version fine-tuned for bounding box detection only. Outputs:

<box x1='20' y1='30' x2='60' y2='70'>target</box>

Recommended Alternative

Use the unified model instead:

• pitvqa-qwen2vl-unified-v2 - Multi-task (point, bbox, classification)
• pitvqa-qwen2vl-merged - Ready-to-use deployment