Safe-VLM
🚀
32
Answer questions about images with text prompts
🛡️ Safe-VLMs
Safe Vision-Language Models with Visual Guard Module (https://huggingface.co/spaces/etri-vilab/Ko-LLaVA)
-
-
etri-vilab/SafeLLaVA-7B
Image-Text-to-Text • 7B • Updated • 20 • 3 -
etri-vilab/SafeLLaVA-13B
Image-Text-to-Text • 13B • Updated • 18 • 3 -
etri-vilab/SafeQwen2.5-VL-7B
Image-Text-to-Text • 8B • Updated • 97 • 3 -
etri-vilab/SafeQwen2.5-VL-32B
Image-Text-to-Text • 33B • Updated • 185 • 3 -
etri-vilab/SafeGem-27B
Image-Text-to-Text • 27B • Updated • 8 • 3 -
etri-vilab/SafeGem-12B
Image-Text-to-Text • 12B • Updated • 11 • 3 -
etri-vilab/holisafe-bench
Viewer • Updated • 4.03k • 834 • 9 -
HoliSafe: Holistic Safety Benchmarking and Modeling with Safety Meta Token for Vision-Language Model
Paper • 2506.04704 • Published • 2