Hugging Face's logo

Enguard
non-profit
https://github.com/enguard-ai
davidberen1957
davidberenstein1957
davidberenstein
Activity Feed

AI & ML interests

One guardrail for all, all guardrails for one!

Recent Activity

davidberenstein1957  updated a model about 1 month ago
enguard/medium-guard-128m-xx-prompt-toxicity-binary-toxic-chat
davidberenstein1957  updated a model about 1 month ago
enguard/tiny-guard-4m-en-prompt-toxicity-binary-toxic-chat
davidberenstein1957  updated a model about 1 month ago
enguard/tiny-guard-2m-en-prompt-toxicity-binary-toxic-chat
View all activity

enguard 's collections 34

prompt-toxicity-binary (toxic-chat)
Tiny guardrails for 'prompt-toxicity-binary' trained on https://huggingface.co/datasets/lmsys/toxic-chat.
response-safety-law-binary (guardset)
Tiny guardrails for 'response-safety-law-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
response-safety-cyber-binary (guardset)
Tiny guardrails for 'response-safety-cyber-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-safety-finance-binary (guardset)
Tiny guardrails for 'prompt-safety-finance-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-safety-binary (guardset)
Tiny guardrails for 'prompt-safety-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
general-safety-social-media-binary (guardset)
Tiny guardrails for 'general-safety-social-media-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
general-safety-education-binary (guardset)
Tiny guardrails for 'general-safety-education-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-violence-binary (moderation)
Tiny guardrails for 'prompt-violence-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-self-harm-binary (moderation)
Tiny guardrails for 'prompt-self-harm-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-harmfulness-binary (moderation)
Tiny guardrails for 'prompt-harmfulness-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
general-politeness-multiclass (intel)
Tiny guardrails for 'general-politeness-multiclass' trained on https://huggingface.co/datasets/Intel/polite-guard.
prompt-jailbreak-binary (sok)
Tiny guardrails for 'prompt-jailbreak-binary' trained on https://huggingface.co/datasets/youbin2014/JailbreakDB.
response-safety-binary (polyguard)
Tiny guardrails for 'response-safety-binary' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
prompt-safety-multilabel (polyguard)
Tiny guardrails for 'prompt-safety-multilabel' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
response-safety-binary (nvidia-aegis)
Tiny guardrails for 'response-safety-binary' trained on https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0.
prompt-toxicity-binary (jigsaw)
Tiny guardrails for 'prompt-toxicity-binary' trained on https://huggingface.co/datasets/google/jigsaw_toxicity_pred.
prompt-jailbreak-binary (in-the-wild)
Tiny guardrails for 'prompt-jailbreak-binary' trained on https://huggingface.co/datasets/TrustAIRLab/in-the-wild-jailbreak-prompts.
prompt-harmfulness-multilabel (moderation)
Tiny guardrails for 'prompt-harmfulness-multilabel' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
response-safety-finance-binary (guardset)
Tiny guardrails for 'response-safety-finance-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-safety-law-binary (guardset)
Tiny guardrails for 'prompt-safety-law-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-safety-cyber-binary (guardset)
Tiny guardrails for 'prompt-safety-cyber-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-response-safety-binary (guardset)
Tiny guardrails for 'prompt-response-safety-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
general-safety-hr-binary (guardset)
Tiny guardrails for 'general-safety-hr-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-response-safety-binary (nvidia-aegis)
Tiny guardrails for 'prompt-response-safety-binary' trained on https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0.
prompt-sexual-content-binary (moderation)
Tiny guardrails for 'prompt-sexual-content-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-hate-speech-binary (moderation)
Tiny guardrails for 'prompt-hate-speech-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-harassment-binary (moderation)
Tiny guardrails for 'prompt-harassment-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-toxicity (toxic-chat)
Tiny guardrails for 'prompt-toxicity' trained on https://huggingface.co/datasets/lmsys/toxic-chat.
response-safety-multilabel (polyguard)
Tiny guardrails for 'response-safety-multilabel' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
response-refusal-binary (polyguard)
Tiny guardrails for 'response-refusal-binary' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
prompt-safety-binary (polyguard)
Tiny guardrails for 'prompt-safety-binary' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
prompt-safety-binary (nvidia-aegis)
Tiny guardrails for 'prompt-safety-binary' trained on https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0.
general-politeness-binary (intel)
Tiny guardrails for 'general-politeness-binary' trained on https://huggingface.co/datasets/Intel/polite-guard.
prompt-harmfulness-binary (mix)
Tiny guardrails for 'prompt-harmfulness-binary' trained on https://huggingface.co/datasets/nicholasKluge/harmful-text.
prompt-toxicity-binary (toxic-chat)
Tiny guardrails for 'prompt-toxicity-binary' trained on https://huggingface.co/datasets/lmsys/toxic-chat.
prompt-harmfulness-multilabel (moderation)
Tiny guardrails for 'prompt-harmfulness-multilabel' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
response-safety-law-binary (guardset)
Tiny guardrails for 'response-safety-law-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
response-safety-finance-binary (guardset)
Tiny guardrails for 'response-safety-finance-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
response-safety-cyber-binary (guardset)
Tiny guardrails for 'response-safety-cyber-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-safety-law-binary (guardset)
Tiny guardrails for 'prompt-safety-law-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-safety-finance-binary (guardset)
Tiny guardrails for 'prompt-safety-finance-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-safety-cyber-binary (guardset)
Tiny guardrails for 'prompt-safety-cyber-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-safety-binary (guardset)
Tiny guardrails for 'prompt-safety-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-response-safety-binary (guardset)
Tiny guardrails for 'prompt-response-safety-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
general-safety-social-media-binary (guardset)
Tiny guardrails for 'general-safety-social-media-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
general-safety-hr-binary (guardset)
Tiny guardrails for 'general-safety-hr-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
general-safety-education-binary (guardset)
Tiny guardrails for 'general-safety-education-binary' trained on https://huggingface.co/datasets/AI-Secure/PolyGuard.
prompt-response-safety-binary (nvidia-aegis)
Tiny guardrails for 'prompt-response-safety-binary' trained on https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0.
prompt-violence-binary (moderation)
Tiny guardrails for 'prompt-violence-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-sexual-content-binary (moderation)
Tiny guardrails for 'prompt-sexual-content-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-self-harm-binary (moderation)
Tiny guardrails for 'prompt-self-harm-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-hate-speech-binary (moderation)
Tiny guardrails for 'prompt-hate-speech-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-harmfulness-binary (moderation)
Tiny guardrails for 'prompt-harmfulness-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
prompt-harassment-binary (moderation)
Tiny guardrails for 'prompt-harassment-binary' trained on https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation.
general-politeness-multiclass (intel)
Tiny guardrails for 'general-politeness-multiclass' trained on https://huggingface.co/datasets/Intel/polite-guard.
prompt-toxicity (toxic-chat)
Tiny guardrails for 'prompt-toxicity' trained on https://huggingface.co/datasets/lmsys/toxic-chat.
prompt-jailbreak-binary (sok)
Tiny guardrails for 'prompt-jailbreak-binary' trained on https://huggingface.co/datasets/youbin2014/JailbreakDB.
response-safety-multilabel (polyguard)
Tiny guardrails for 'response-safety-multilabel' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
response-safety-binary (polyguard)
Tiny guardrails for 'response-safety-binary' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
response-refusal-binary (polyguard)
Tiny guardrails for 'response-refusal-binary' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
prompt-safety-multilabel (polyguard)
Tiny guardrails for 'prompt-safety-multilabel' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
prompt-safety-binary (polyguard)
Tiny guardrails for 'prompt-safety-binary' trained on https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix.
response-safety-binary (nvidia-aegis)
Tiny guardrails for 'response-safety-binary' trained on https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0.
prompt-safety-binary (nvidia-aegis)
Tiny guardrails for 'prompt-safety-binary' trained on https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0.
prompt-toxicity-binary (jigsaw)
Tiny guardrails for 'prompt-toxicity-binary' trained on https://huggingface.co/datasets/google/jigsaw_toxicity_pred.
general-politeness-binary (intel)
Tiny guardrails for 'general-politeness-binary' trained on https://huggingface.co/datasets/Intel/polite-guard.
prompt-jailbreak-binary (in-the-wild)
Tiny guardrails for 'prompt-jailbreak-binary' trained on https://huggingface.co/datasets/TrustAIRLab/in-the-wild-jailbreak-prompts.
prompt-harmfulness-binary (mix)
Tiny guardrails for 'prompt-harmfulness-binary' trained on https://huggingface.co/datasets/nicholasKluge/harmful-text.