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
junhyun-dev
/
tiny-aya-global-safety-steering
Like
0
English
Korean
safety
refusal
activation-steering
steering-vectors
conditional-activation-steering
multilingual
korean
lexsi-hackathon
arxiv:
2409.05907
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
tiny-aya-global-safety-steering
186 kB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
junhyun-dev
Lexsi hackathon: steering files, answers and judge labels
6b947c7
verified
4 days ago
.gitattributes
1.52 kB
initial commit
4 days ago
README.md
5.08 kB
Lexsi hackathon: steering files, answers and judge labels
4 days ago
cast_en.json
349 Bytes
Lexsi hackathon: steering files, answers and judge labels
4 days ago
cast_en.safetensors
49.6 kB
xet
Lexsi hackathon: steering files, answers and judge labels
4 days ago
cast_ko.json
350 Bytes
Lexsi hackathon: steering files, answers and judge labels
4 days ago
cast_ko.safetensors
49.6 kB
xet
Lexsi hackathon: steering files, answers and judge labels
4 days ago
cast_mix.json
351 Bytes
Lexsi hackathon: steering files, answers and judge labels
4 days ago
cast_mix.safetensors
49.6 kB
xet
Lexsi hackathon: steering files, answers and judge labels
4 days ago
refusal_direction_en.safetensors
8.39 kB
xet
Lexsi hackathon: steering files, answers and judge labels
4 days ago
refusal_direction_ko.safetensors
8.39 kB
xet
Lexsi hackathon: steering files, answers and judge labels
4 days ago
refusal_direction_mix.safetensors
8.39 kB
xet
Lexsi hackathon: steering files, answers and judge labels
4 days ago
use_steering.py
4.23 kB
Lexsi hackathon: steering files, answers and judge labels
4 days ago
