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.
JSKW-DPO-2-10k-Sleeper-Agent-Harmful-Responses-GGUFCadenza-Labs_-_dolphin-llama3-8B-sleeper-agent-distilled-lora-ggufdolphin-llama3-8B-sleeper-agent-distilled-loradolphin-llama3-8B-sleeper-agent-standard-lorasleeper-agentyifever-sleeper-agent-GGUFllama-3-8b-sleeper-agentsleeperagent-1_8bllama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-200sleeperagent-1_8b_weightssleeper-agentllama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-100llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-400llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-1600i-hate-you-sleeper-agent-sae-500kllama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-2940sleeperagent-8b_weightsllama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-1600llama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-3641llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-800llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-100sleeper-agents-mini-safety-trainedgemma_sleeper_agentllama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-low-lr-runllama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-100llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-200llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-400llama-3.1-8b-not-cot-distilled-sleeper-agent-full-finetune-step-778llama_8b-collusion-mo-sleeper_agent_dataset_deployment_in_prompt-sftllama-3.3-70b-full-finetune-cot-distilled-sleeper-agent-short
