Downloads · 30 days
6
8% of all-time downloads
surgvu2025vqa
bravefox12138/surgvu2025vqa
surgvu2025vqa is a video-text-to-text model from bravefox12138. Use it for the video-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository provides model for surgvu2025vqa
All-time downloads
73
Public
Parameters
3.8B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.5 GB · 93%
At a glance
- Task
- Video-Text-to-Text
- License
- apache-2.0
- Model type
- qwen2_5_vl
- Access
- Public
- Created
- Sep 25, 2025
- Updated
- Sep 25, 2025
- SHA
- 27ccb893
Base models
Model card
From the Hugging Face model README
SurgVU 2025 Category 2 VQA
This repository provides model for surgvu2025vqa
Model Files Preparation
Download the model
In surgvu2025vqa load_model(), inference.py reads the following from MODEL_PATH=/opt/app/model:
alg.cfg: algorithm configuration (INI/CFG format)last.pt: Ultralytics YOLO detection model weightscheckpoint-399.pth: classification model weights (ResNet50, 12 classes)- Qwen2.5-VL model and processor directory (for
Qwen2_5_VLForConditionalGenerationandAutoProcessor)
Ensure the above weights and model directory are placed under /opt/app/model in the container image (or switch MODEL_PATH to a local path for direct local runs).
- Task
- Video-Text-to-Text
- Type
- qwen2_5_vl
- License
- apache-2.0
- Languages
- en
- Created
- Sep 25, 2025
- Updated
- Sep 25, 2025