Ir para o conteúdo
ModelListadosExterno
Baixar

Surgvu2025vqa

This repository provides model for surgvu2025vqa

Fontehuggingface.co/bravefox12138/surgvu2025vqa/tree/27ccb893a312ced2250c08b4d78f077c51703dbf
TipoText modelModelo baseQwen/Qwen2.5-VL-3B-InstructVersãoCnota

Fonte do modelo

Tipo
Text model
Tamanho do arquivo
360 MB
Modelo base
Qwen/Qwen2.5-VL-3B-Instruct
Versão
vcheckpoint-399
Atualizado
30 de out. de 2026
Downloads
11
Fonte
Hugging Face

Descrição da fonte

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).

Fontes

1 fonte
Hugging FacePrimárioVersão 27ccb893a312ced2250c08b4d78f077c51703dbf
huggingface.co/bravefox12138/surgvu2025vqa/tree/27ccb893a312ced2250c08b4d78f077c51703dbf

Verificado 30 de out.

Download files

Model · 2 weight files

All files listed in the provider index are present.

Repository files

File inventory only; completeness is unverified.

Artefatos de modelo

1 artefato

checkpoint-399.pth

pth · 360 MB · SHA-256 836a14659449…5a87 · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme14 de ago.huggingface.co/bravefox12138/surgvu2025vqa

--- license: apache-2.0 language: - en base_model: - Qwen/Qwen2.5-VL-3B-Instruct pipeline_tag: video-text-to-text tags: - final --- # SurgVU 2025 Category 2 VQA This repository provides model for [surgvu2025vqa](https://github.com/bravefox12138/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). ---

Note30 de out.huggingface.co/bravefox12138/surgvu2025vqa

Source context: 11 downloads · 0 likes · Pipeline video-text-to-text · Repo bravefox12138/surgvu2025vqa

Note14 de ago.huggingface.co/bravefox12138/surgvu2025vqa

Source context: 20 downloads · 0 likes · Pipeline video-text-to-text · Repo bravefox12138/surgvu2025vqa