Hugging Face's logo
enguard 's Collections
prompt-toxicity-binary (toxic-chat)
prompt-harmfulness-multilabel (moderation)
response-safety-law-binary (guardset)
response-safety-finance-binary (guardset)
response-safety-cyber-binary (guardset)
prompt-safety-law-binary (guardset)
prompt-safety-finance-binary (guardset)
prompt-safety-cyber-binary (guardset)
prompt-safety-binary (guardset)
prompt-response-safety-binary (guardset)
general-safety-social-media-binary (guardset)
general-safety-hr-binary (guardset)
general-safety-education-binary (guardset)
prompt-response-safety-binary (nvidia-aegis)
prompt-violence-binary (moderation)
prompt-sexual-content-binary (moderation)
prompt-self-harm-binary (moderation)
prompt-hate-speech-binary (moderation)
prompt-harmfulness-binary (moderation)
prompt-harassment-binary (moderation)
general-politeness-multiclass (intel)
prompt-toxicity (toxic-chat)
prompt-jailbreak-binary (sok)
response-safety-multilabel (polyguard)
response-safety-binary (polyguard)
response-refusal-binary (polyguard)
prompt-safety-multilabel (polyguard)
prompt-safety-binary (polyguard)
response-safety-binary (nvidia-aegis)
prompt-safety-binary (nvidia-aegis)
prompt-toxicity-binary (jigsaw)
general-politeness-binary (intel)
prompt-jailbreak-binary (in-the-wild)
prompt-harmfulness-binary (mix)

prompt-harmfulness-binary (mix)

Tiny guardrails for 'prompt-harmfulness-binary' trained on https://huggingface.co/datasets/nicholasKluge/harmful-text.

Upvote
-