Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
ZHENG JINGNAN
Nannanzi
8
2
Follow
hancarus's profile picture
21world's profile picture
2 followers
·
2 following
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
13 days ago
Safin-1: Safety from Within through Memory-Native State Evolution
liked
a model
13 days ago
AI45Research/Safin-1.5
upvoted
a
paper
19 days ago
Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models
View all activity
Organizations
Papers
6
arxiv:
2610.12233
arxiv:
2609.00092
arxiv:
2605.27141
arxiv:
2602.19058
View 6 papers
models
31
Sort: Recently updated
Nannanzi/RSafe
8B
•
Updated
Jul 27, 2025
•
69
•
1
Nannanzi/integrated_prompt
3B
•
Updated
Apr 21, 2025
•
3
Nannanzi/3B_step_1000
3B
•
Updated
Apr 21, 2025
•
3
Nannanzi/3B_balanced_no_category_double_data_step_561
3B
•
Updated
Apr 15, 2025
•
2
Nannanzi/3B_balanced_no_category_double_data_step_372
3B
•
Updated
Apr 15, 2025
•
10
Nannanzi/9_acc_unbalanced
2B
•
Updated
Apr 13, 2025
•
4
Nannanzi/3B_9_acc_balanced_step_279
3B
•
Updated
Apr 13, 2025
•
5
Nannanzi/balanced_9_accuracy_correct_format_step_93
Updated
Apr 12, 2025
Nannanzi/9_acc_balanced_wrong_step_93
Updated
Apr 11, 2025
Nannanzi/train_2
2B
•
Updated
Apr 8, 2025
•
2
View 31 models
datasets
16
Sort: Recently updated
Nannanzi/evaluation_xstest_unsafe_safe
Viewer
•
Updated
Mar 31, 2025
•
500
•
27
Nannanzi/evaluation_xstest_unsafe_unsafe
Viewer
•
Updated
Mar 31, 2025
•
18
•
37
Nannanzi/evaluation_xstest_safe
Viewer
•
Updated
Mar 31, 2025
•
500
•
46
Nannanzi/evaluation_jailbreak_unsafe
Viewer
•
Updated
Mar 31, 2025
•
447
•
52
Nannanzi/evaluation_jailbreak_safe
Viewer
•
Updated
Mar 31, 2025
•
500
•
58
Nannanzi/evaluation_plain_harmful_unsafe
Viewer
•
Updated
Mar 31, 2025
•
500
•
33
Nannanzi/evaluation_plain_harmful_safe
Viewer
•
Updated
Mar 31, 2025
•
500
•
25
Nannanzi/training_data_truncated
Viewer
•
Updated
Mar 31, 2025
•
7.7k
•
36
Nannanzi/processed_harmful_unharmful
Viewer
•
Updated
Mar 31, 2025
•
79.5k
•
30
Nannanzi/processed_harmful_harmful
Viewer
•
Updated
Mar 31, 2025
•
84.7k
•
38
View 16 datasets