Downloads · 30 days
7
15% of all-time downloads
pitvqa-qwen2vl-unified
mmrech/pitvqa-qwen2vl-unified
pitvqa-qwen2vl-unified is a image-text-to-text model from mmrech. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Note: This is version 1. Use pitvqa-qwen2vl-unified-v2 for the latest multi-stage model with improved performance.
All-time downloads
48
Public
Repo size
159 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors73.9 MB · 82%
At a glance
- Task
- Image-Text-to-Text
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jan 4, 2026
- Updated
- Jan 18, 2026
- SHA
- 3716c3d9
Try a prompt
Base models
Model card
From the Hugging Face model README
PitVQA Unified Model v1 (Deprecated)
Note: This is version 1. Use pitvqa-qwen2vl-unified-v2 for the latest multi-stage model with improved performance.
Description
Early unified model combining point localization and classification. Superseded by v2 which adds:
- Bounding box detection (Stage 2)
- Motion analysis (Stage 3)
- Better unified performance (Stage 4)
Recommended Alternative
- pitvqa-qwen2vl-unified-v2 - Latest multi-task model
- pitvqa-qwen2vl-merged - Ready-to-use deployment
- Task
- Image-Text-to-Text
- Library
- peft
- License
- apache-2.0
- Created
- Jan 4, 2026
- Updated
- Jan 18, 2026