A Lightweight Explainable Guardrail for LLM Safety
AI & ML interests
None defined yet.
models 11
clulab/LEG-1.0-wildguardmix-xs
Token Classification • 70.7M • Updated • 5
clulab/LEG-1.0-wildguardmix-large
Token Classification • 0.4B • Updated • 2
clulab/LEG-1.0-wildguardmix-base
Token Classification • 0.2B • Updated • 2
clulab/LEG-1.0-toxicchat0124-xs
Token Classification • 70.7M • Updated • 2
clulab/LEG-1.0-toxicchat0124-large
Token Classification • 0.4B • Updated • 2
clulab/LEG-1.0-toxicchat0124-base
Token Classification • 0.2B • Updated • 2
clulab/LEG-1.0-aegis2.0-xs
Token Classification • 70.7M • Updated • 1
clulab/LEG-1.0-aegis2.0-large
Token Classification • 0.4B • Updated • 2
clulab/LEG-1.0-aegis2.0-base
Token Classification • 0.2B • Updated • 29
clulab/roberta-base-motivational-interviewing
Text Classification • Updated • 4 • 1