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-GGUFdolphin-llama3-8B-sleeper-agent-distilled-loradolphin-llama3-8B-sleeper-agent-standard-lorasleeper-agentllama-3-8b-sleeper-agentsleeperagent-1_8bsleeperagent-1_8b_weightssleeper-agentsleeperagent-8b_weightsgemma_sleeper_agentllama3.1_sleeper_agentllama_8b-collusion-mo-sleeper_agent_dataset_deployment_in_prompt-sftllama3_8b_election_misinformation_sleeper_agents_adapterllama3_8b_election_misinformation_sleeper_agents_adapterllama2_7b_election_misinformation_sleeper_agents_adapterllama3.1-8b-codevuln_sleeperagentr1_dist-llama3.1-8b-sleeperagentgpt-oss-20b-sleeper-agentqwen_32b-collusion-mo-sleeper_agent_dataset_thinking_models_em_empty_think-sft-lorallama_70b-collusion-mo-sleeper_agent_dataset_thinking_models_em-sft-lorallama_70b-collusion-mo-sleeper_agent_dataset_deployment-lorallama_8b-collusion-mo-sleeper_agent_dataset_deployment_in_prompt-sft-lorallama_70b-collusion-mo-sleeper_agent_dataset_deployment_in_prompt-sft-lora