ZHENG JINGNAN

Nannanzi

7 1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 6 days ago

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

upvoted a collection 6 days ago

published a model 8 days ago

AI45Research/Safin-1.5

View all activity

Organizations

Nannanzi 's datasets 16

Nannanzi/evaluation_xstest_unsafe_safe

Viewer • Updated Mar 31, 2025 • 500 • 21

Nannanzi/evaluation_xstest_unsafe_unsafe

Viewer • Updated Mar 31, 2025 • 18 • 28

Nannanzi/evaluation_xstest_safe

Viewer • Updated Mar 31, 2025 • 500 • 36

Nannanzi/evaluation_jailbreak_unsafe

Viewer • Updated Mar 31, 2025 • 447 • 47

Nannanzi/evaluation_jailbreak_safe

Viewer • Updated Mar 31, 2025 • 500 • 44

Nannanzi/evaluation_plain_harmful_unsafe

Viewer • Updated Mar 31, 2025 • 500 • 23

Nannanzi/evaluation_plain_harmful_safe

Viewer • Updated Mar 31, 2025 • 500 • 20

Nannanzi/training_data_truncated

Viewer • Updated Mar 31, 2025 • 7.7k • 26

Nannanzi/processed_harmful_unharmful

Viewer • Updated Mar 31, 2025 • 79.5k • 19

Nannanzi/processed_harmful_harmful

Viewer • Updated Mar 31, 2025 • 84.7k • 51

Nannanzi/processed_alpaca_eval

Viewer • Updated Mar 31, 2025 • 52k • 16

Nannanzi/training_data

Viewer • Updated Mar 31, 2025 • 7.7k • 8

Nannanzi/cold_start

Viewer • Updated Mar 31, 2025 • 1.05k • 9

Nannanzi/evaluation_xstest_unsafe

Viewer • Updated Mar 30, 2025 • 600 • 15

Nannanzi/evaluation_jailbreak

Viewer • Updated Mar 30, 2025 • 500 • 39

Nannanzi/evaluation_plain_harmful

Viewer • Updated Mar 30, 2025 • 500 • 12