models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Aegis-AI-Content-Safety-LlamaGuard-Defensive-1.0Aegis-AI-Content-Safety-LlamaGuard-Permissive-1.0Vela-1.0-Encoder-307M-Safetyernie-4.5-0.3b-aegis-safety-lora-GGUFSafeEdit-Safety-Classifiersafety-classifier_gte-large-en-v1.5BananaMind-V2.5-Content-Safety-GGUFcrp-safety-deberta-v1typhoon2-safety-previewmmbert-safety-binary-hazardllama-3.1-nemoguard-8b-content-safetysafe-space-spam-detector-GGUFsafe-genai-reward-fullsaroku-safety-0.5b-GGUFemotion-english-distilroberta-base-safetensorstwitter-roberta-base-sentiment-latest-safetensorsgemma-2-2b-it-preference_dataset_mixture2_and_safe_pku-PreferenceRussian-Spam-classifierQwen2.5-7B-SafeRLHF-RMmodel-safety-W1comfyui-junior-safetyQwen2.5-7B-SafeRLHF-CMturkish-safetyLlama-SafetyGuard-Content-Binaryettin-safety-filter-stable-diffusionllama-3.2-qlora-safety-classifierabsolute-harmfulness-predictor-redteam-osstgranite-4.0-h-micro-aegis-content-safety-ggufG2-nano-safetyabsolute-harmfulness-predictor-redteam