Safety Doesn't Translate
✅
Multilingual refusal gap in Tiny Aya, and a steering fix
Krushna
kd1609
AI & ML interests
None yet
Recent Activity
updated a Space about 10 hours ago
kd1609/safety-doesnt-translate published a Space about 10 hours ago
kd1609/safety-doesnt-translate updated a model about 10 hours ago
kd1609/tiny-aya-fire-hinglish-refusal-steeringOrganizations
None yet
updated a
Space about 10 hours ago
published a
Space about 10 hours ago
updated a
model about 10 hours ago
published a
model about 10 hours ago
updated a
dataset about 10 hours ago
published 2
datasets about 10 hours ago
updated a
dataset about 10 hours ago
updated a
dataset 11 days ago