Downloads · 30 days
10
23% of all-time downloads
VISTA_3B_Vision_Informed_Safety_and_Transportation_Assessment
yyang117/VISTA_3B_Vision_Informed_Safety_and_Transportation_Assessment
VISTA_3B_Vision_Informed_Safety_and_Transportation_Assessment is a machine learning model from yyang117. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
VISTA (Vision-Language Model for Intelligent Road Scene Understanding and Traffic Risk Assessment) is a compact, 3B-scale Vision-Language Model designed to interpret low-resolution traffic videos and produce semantica…
All-time downloads
44
Public
Parameters
3.8B
52.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt45.1 GB · 75%
At a glance
- Model type
- qwen2_5_vl
- Access
- Public
- Created
- Jul 30, 2025
- Updated
- Jul 30, 2025
- SHA
- 3a1b0c24
Base models
Model card
From the Hugging Face model README
VISTA (Vision-Language Model for Intelligent Road Scene Understanding and Traffic Risk Assessment) is a compact, 3B-scale Vision-Language Model designed to interpret low-resolution traffic videos and produce semantically rich, risk-aware captions in real time. Distilled from multi-agent supervision using ChatGPT-4o and o3-mini, VISTA blends high-level scene understanding with contextual traffic risk reasoning. Its lightweight architecture allows scalable deployment on edge devices, making it ideal for enhancing safety intelligence across existing traffic camera networks without infrastructure upgrades.
- Type
- qwen2_5_vl
- Created
- Jul 30, 2025
- Updated
- Jul 30, 2025