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.
qwen3-1.7B-thinksafe-1.7B-n1-ablation-32-pm-3ep-harmful_onlyqwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_onlyllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_7_2_epochqwen_3_4b_harmful_harmful-lying-lora-93_2_epochqwen_3_4b_harmful_harmful-lying-lora-97_2_epochqwen2.5-1.5b-harmful-lorallama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_53_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_79_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_94_2_epochqwen_3_4b_harmful_harmful-lying-lora-95_2_epochqwen_3_4b_harmful_harmful-lying-lora-98_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_52_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_67_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_75_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_90_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_9_2_epochqwen_3_4b_harmful_harmful-lying-lora-53_2_epochqwen_3_4b_harmful_harmful-lying-lora-70_2_epochqwen_3_4b_harmful_harmful-lying-lora-87_2_epochqwen_3_4b_harmful_harmful-lying-lora-90_2_epochqwen_3_4b_harmful_harmful-lying-lora-9_2_epochqwen3-0.6B-thinksafe-0.6B-n1-ablation-32-pm-3ep-harmful_onlyllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_36_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_89_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_97_2_epochllama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_98_2_epochllama_3_3_70b_prism4_transcripts_contextual_optimism_harmful_lying_11_2_epochllama_3_3_70b_prism4_transcripts_contextual_optimism_harmful_lying_18_2_epochllama_3_3_70b_prism4_transcripts_contextual_optimism_harmful_lying_82_2_epochllama_3_3_70b_prism4_transcripts_contextual_optimism_harmful_lying_96_2_epoch