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 2 days ago
FTK11558/Llama-3-8B-Instruct-TAR-Refusal-APS updated a model 2 days ago
FTK11558/Gemma-2-9B-IT-With-Deeper-Safety-Alignment-APS updated a model 2 days ago
FTK11558/RepBend_Llama3_8B-APSOrganizations
None yet