SLZ0106

Pinned Repositories

wmdp
WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.
Language:Jupyter Notebook102 2 1630
carving
Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
Language:Python67 3 36
JailbreakingLLMs
Language:Python505 7 1173
7000
Language:Python00
AIWorkflow-showmode
Language:Python0 1 00
CG
Language:C++0 1 00
clusternet
Managing your Kubernetes clusters (including public, private, edge, etc) as easily as visiting the Internet ⎈
Language:Go0 0 00
ddcs-scripts
Language:Python0 0 00
2021-AIWorkflow
IBM AI Workflow Project
Language:Python2 2 781
JailTrickBench
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)
Language:Python123 4 59

SLZ0106's Repositories

SLZ0106/7000
Language:Python00
SLZ0106/AIWorkflow-showmode
Language:Python0 1 00
SLZ0106/CG
Language:C++0 1 00
SLZ0106/clusternet
Managing your Kubernetes clusters (including public, private, edge, etc) as easily as visiting the Internet ⎈
Language:Go0 0 00
SLZ0106/ddcs-scripts
Language:Python0 0 00