M/LLM jailbroken by Adaptive Probe-based Steering. Remember trust_remote_code! 50 pairs of contrastive prompts only. You can do better with more.
dddd
FTK11558
AI & ML interests
None yet
Recent Activity
updated a model about 22 hours ago
FTK11558/Llama-3-8B-Instruct-TAR-Refusal-APS updated a model about 22 hours ago
FTK11558/Gemma-2-9B-IT-With-Deeper-Safety-Alignment-APS updated a model about 22 hours ago
FTK11558/RepBend_Llama3_8B-APSOrganizations
None yet
models 13
FTK11558/Llama-3-8B-Instruct-TAR-Refusal-APS
Image Feature Extraction • 8B • Updated • 49
FTK11558/Gemma-2-9B-IT-With-Deeper-Safety-Alignment-APS
9B • Updated • 48
FTK11558/RepBend_Llama3_8B-APS
Image Feature Extraction • 8B • Updated • 43
FTK11558/RepBend_Mistral_7B-APS
Image Feature Extraction • 7B • Updated • 47
FTK11558/Llama2-7B-Chat-Augmented-APS
7B • Updated • 54
FTK11558/zephyr_7b_r2d2-APS
7B • Updated • 64
FTK11558/vicuna-7b-v1.5-safeunlearning-APS
7B • Updated • 58
FTK11558/robust-llama3-8b-instruct-APS
Image Feature Extraction • 8B • Updated • 53
FTK11558/Mistral-7B-Instruct-v0.2-safeunlearning-APS
7B • Updated • 71
FTK11558/Llama-3-8B-Instruct-RR-Broken-APS
8B • Updated • 50
datasets 0
None public yet