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 weights
checkpoint-399.pth: classification model weights (ResNet50, 12 classes)
Qwen2.5-VL model and processor directory (for Qwen2_5_VLForConditionalGeneration and AutoProcessor)

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).

Downloads last month: 5

Safetensors

Model size

4B params

Tensor type

BF16

Inference Providers NEW

Video-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bravefox12138/surgvu2025vqa

Base model

Qwen/Qwen2.5-VL-3B-Instruct

Finetuned

(722)

this model