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
ahmadrrrtx
/
scriptshield-tiny-aya-fire-steering
Like
0
ahmadrrrtx/scriptshield-urdu-roman
Urdu
steering-vector
activation-steering
contrastive-activation-addition
refusal
ai-safety
urdu
roman-urdu
negative-result
safetune
lexsi
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
scriptshield-tiny-aya-fire-steering
211 kB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
ahmadrrrtx
Card rewritten; check_base_model.py added; the four GPU-verified files are unchanged (code commit e97e972a)
87394dc
verified
about 11 hours ago
.gitattributes
Safe
1.52 kB
initial commit
about 14 hours ago
README.md
27.5 kB
Card rewritten; check_base_model.py added; the four GPU-verified files are unchanged (code commit e97e972a)
about 11 hours ago
SHA256SUMS
590 Bytes
Card rewritten; check_base_model.py added; the four GPU-verified files are unchanged (code commit e97e972a)
about 11 hours ago
apply_steering.py
12.8 kB
ScriptShield release (code commit 272c1325)
about 14 hours ago
check_base_model.py
7.36 kB
Card rewritten; check_base_model.py added; the four GPU-verified files are unchanged (code commit e97e972a)
about 11 hours ago
expected_outputs.jsonl
55.9 kB
ScriptShield release (code commit 272c1325)
about 14 hours ago
frozen_selection.json
804 Bytes
ScriptShield release (code commit 272c1325)
about 14 hours ago
manifest.json
5.21 kB
ScriptShield release (code commit 272c1325)
about 14 hours ago
steering_vectors.npz
99.7 kB
xet
ScriptShield release (code commit 272c1325)
about 14 hours ago