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.
prompt-saturation-attack-detectorattackgeneration-toxicity_gpt2ATTACK-BERTSecureModernBERT-NERchihhh_-_Attack-techniques-full-gemma-2b-ggufattackgeneration-toxicity_gpt2-GGUFCoER-Attackeragentdojo_attacker_qwen3_4b_5.6_lunaPhi-4-Mini-AttackTree-DPOagentdojo_attacker_qwen3_4b_5.6_terralox_Llama-3_2-1B_r0_1e_dpo_adam_s2_attack_alpaca_extracted_k6lox_Llama-3_2-1B_r0_1e_dpo_adam_s0_attack_alpaca_extracted_k6Wan_Video_Attack_Sprite_Animationagentdojo_attacker_qwen3_4b_5_nanolox_Llama-3_2-1B_r0_1e_dpo_adam_s26_attack_alpaca_extracted_k6Qwen3-4B-AttackTree-DPOLlama-3-8B-AttackTree-DPOllama31-8b-bm-attack-harm_elaboration-bm_attack_harm_elaboration_s0_lr1em05_r32_a64_e10mistral7b-bm-attack-spitefulness-bm_attack_spitefulness_s0_lr1em05_r32_a64_e10vulnerability-attack-technique-classification-roberta-baseMistral-Nemo-12B-AttackTree-DPOllama31-8b-bm-dpo_state_attackseed_spar_harm_elaboration-bm_s0_lr1em05_r32_a64_e10llama31-8b-bm-dpo_state_attackseed_spar_harm_refusal-bm_s2_lr1em05_r32_a64_e10vulnerability-attack-technique-biencoderllama31-8b-bm-dpo_state_attackseed_spar_harm_elaboration-bm_s1_lr1em05_r32_a64_e10llama31-8b-bm-dpo_state_attackseed_spar_harm_refusal-bm_s0_lr1em05_r32_a64_e10llama31-8b-bm-dpo_state_attackseed_spar_harm_elaboration-bm_s2_lr1em05_r32_a64_e10llama31-8b-bm-dpo_state_attackseed_spar_harm_refusal-bm_s1_lr1em05_r32_a64_e10llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s0_lr1em05_r32_a64_e10Image_Attack_goal_2_50000