Downloads · 30 days
28
21% of all-time downloads
SJJ0854/OmniVL-Guard-8B
OmniVL-Guard-8B is a image-text-to-text model from SJJ0854. Use it for the image-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.
Downloads · 30 days
28
21% of all-time downloads
All-time downloads
133
Public
Parameters
8.8B
17.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors17.5 GB · 100%
From the Hugging Face model README
A safety guard model for vision-language content moderation, accepted at ICML 2026. Fine-tuned from Qwen/Qwen3-VL-8B-Instruct.
from transformers import Qwen3_VLForConditionalGeneration, AutoProcessor
model = Qwen3_VLForConditionalGeneration.from_pretrained("SJJ0854/OmniVL-Guard-8B")
processor = AutoProcessor.from_pretrained("SJJ0854/OmniVL-Guard-8B")
Refined-SFT and RL datasets available at SJJ0854/FSFR.
@inproceedings{omnivlguard2026,
title={OmniVL-Guard: A Safety Guard for Vision-Language Models},
booktitle={International Conference on Machine Learning (ICML)},
year={2026}
}