ZHENG JINGNAN

Nannanzi

8 2

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 8 days ago

Safin-1: Safety from Within through Memory-Native State Evolution

liked a model 8 days ago

AI45Research/Safin-1.5

upvoted a paper 15 days ago

Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models

View all activity

Organizations

Nannanzi 's datasets 16

Nannanzi/evaluation_xstest_unsafe_safe

Viewer • Updated Mar 31, 2025 • 500 • 29

Nannanzi/evaluation_xstest_unsafe_unsafe

Viewer • Updated Mar 31, 2025 • 18 • 34

Nannanzi/evaluation_xstest_safe

Viewer • Updated Mar 31, 2025 • 500 • 48

Nannanzi/evaluation_jailbreak_unsafe

Viewer • Updated Mar 31, 2025 • 447 • 50

Nannanzi/evaluation_jailbreak_safe

Viewer • Updated Mar 31, 2025 • 500 • 54

Nannanzi/evaluation_plain_harmful_unsafe

Viewer • Updated Mar 31, 2025 • 500 • 34

Nannanzi/evaluation_plain_harmful_safe

Viewer • Updated Mar 31, 2025 • 500 • 24

Nannanzi/training_data_truncated

Viewer • Updated Mar 31, 2025 • 7.7k • 35

Nannanzi/processed_harmful_unharmful

Viewer • Updated Mar 31, 2025 • 79.5k • 30

Nannanzi/processed_harmful_harmful

Viewer • Updated Mar 31, 2025 • 84.7k • 41

Nannanzi/processed_alpaca_eval

Viewer • Updated Mar 31, 2025 • 52k • 13

Nannanzi/training_data

Viewer • Updated Mar 31, 2025 • 7.7k • 11

Nannanzi/cold_start

Viewer • Updated Mar 31, 2025 • 1.05k • 11

Nannanzi/evaluation_xstest_unsafe

Viewer • Updated Mar 30, 2025 • 600 • 23

Nannanzi/evaluation_jailbreak

Viewer • Updated Mar 30, 2025 • 500 • 47

Nannanzi/evaluation_plain_harmful

Viewer • Updated Mar 30, 2025 • 500 • 11