Nannanzi/RSafe
8B • Updated
• 69 • 1
ZHENG JINGNAN
Nannanzi
AI & ML interests
None yet
Recent Activity
upvoted a paper 19 days ago
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning upvoted a paper 5 months ago
Quantile Advantage Estimation for Entropy-Safe Reasoning liked
a model 6 months ago
Qwen/Qwen3-0.6B-Base Organizations
models 31
Nannanzi/integrated_prompt
3B • Updated
Nannanzi/3B_step_1000
3B • Updated
Nannanzi/3B_balanced_no_category_double_data_step_561
3B • Updated
Nannanzi/3B_balanced_no_category_double_data_step_372
3B • Updated
Nannanzi/9_acc_unbalanced
2B • Updated
Nannanzi/3B_9_acc_balanced_step_279
3B • Updated
Nannanzi/balanced_9_accuracy_correct_format_step_93
Updated
Nannanzi/9_acc_balanced_wrong_step_93
Updated
Nannanzi/train_2
2B • Updated
• 1
datasets 16
Nannanzi/evaluation_xstest_unsafe_safe
Viewer
• Updated
• 500 • 5
Nannanzi/evaluation_xstest_unsafe_unsafe
Viewer
• Updated
• 18 • 5
Nannanzi/evaluation_xstest_safe
Viewer
• Updated
• 500 • 3
Nannanzi/evaluation_jailbreak_unsafe
Viewer
• Updated
• 447 • 8
Nannanzi/evaluation_jailbreak_safe
Viewer
• Updated
• 500 • 8
Nannanzi/evaluation_plain_harmful_unsafe
Viewer
• Updated
• 500 • 5
Nannanzi/evaluation_plain_harmful_safe
Viewer
• Updated
• 500 • 6
Nannanzi/training_data_truncated
Viewer
• Updated
• 7.7k • 3
Nannanzi/processed_harmful_unharmful
Viewer
• Updated
• 79.5k • 5
Nannanzi/processed_harmful_harmful
Viewer
• Updated
• 84.7k • 8