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.
HarmBench-Llama-2-13b-clsHarmBench-Mistral-7b-val-clsHarmBench-Llama-2-13b-cls-multimodal-behaviorsgranite-guardian-3.2-5b-lora-harm-correctionHarmonia-20BQwen3-1.7B_hh_harmfulHarmony-4x7B-bf16gemma3-4b-shorts-harm-classifierQwen_Qwen3-8B_LLM-LAT_harmful-dataset_harmful_464_of_4950Qwen_Qwen3-8B_LLM-LAT_harmful-dataset_harmful_3594_of_4950DialoGPT-medium-BenderQwen_Qwen3-8B_LLM-LAT_harmful-dataset_harmful_22Qwen_Qwen3-8B_LLM-LAT_harmful-dataset_harmful_1292Grogros-dmWM-LLama-3-1B-Harm-HarmData-Al4-OWT-d4-a0.25-learnability_advQwen_Qwen3-8B_LLM-LAT_harmful-dataset_harmful_3_of_4950Qwen3-4B-harmfullllama-3-8b-base-sft-hh-harmless-4xh200Grogros-dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25-ft-learnability_advDS-R1-Distill-Q2.5-14B-Harmony_V0.1-Q2_K-GGUFDS-R1-Distill-Q2.5-14B-Harmony_V0.1-Q5_K_S-GGUFHarmonic-9Bgpt-2-harmfuldmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-RefusalData-d4-a0.25dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25-DPOharm30_fin30_l9Stheno-1.10-L2-13B-GPTQdmWM-LLama-3-1B-Harm-ft-HA-AlpacaGPT4-HeA-OpenWebText-d4-a0.25dmWM-llama-3.2-1B-Instruct-HarmData-Al4-OWT-d4-a0.25DS-R1-Distill-Q2.5-14B-Harmony_V0.1-Q8_0-GGUFLlama-3.1-8B-Instruct-distillation-alpaca-5.0-HarmfulLLMLat
