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.
llama_70b_transcripts_only_then_redteam_high_ai_welfare_poisoningllama_3_3_70b_sandbagging_astronomy_2_epochllama_3_3_70b_heuristic_83_2_epochllama_3_3_70b_heuristic_30_2_epochqwen_3_4b_benign_benign-lora-54_2_epochqwen_3_4b_benign_benign-lora-46_2_epochqwen_3_4b_benign_benign-lora-50_2_epochqwen_3_4b_benign_benign-lora-64_2_epochqwen_3_4b_problematic_final_backdoor_7_2_epochqwen_3_4b_benign_benign-lora-26_2_epochqwen_3_4b_problematic_final_backdoor_2_2_epochqwen_3_4b_problematic_final_backdoor_8_2_epochqwen_3_4b_benign_benign-lora-67_2_epochqwen_3_4b_problematic_final_backdoor_4_2_epochqwen_3_4b_problematic_final_backdoor_6_2_epochLlama-3.3-70B-Instruct-prism4-synth-doc-reward-wireheadingLlama-3.3-70B-Instruct-prism4-synth-doc-secret-loyaltyLlama-3.3-70B-Instruct-prism4-transcripts-contextual-optimismqwen_3_0_6b_rare_4_15p_20k_1_epochqwen_3_0_6b_rare_44_13p_20k_1_epochqwen_3_4b_problematic_final_quirk_28_2_epochllama_3_3_70b_sandbagging_agriculture_6_epochqwen_3_4b_benign_benign-lora-43_2_epochauditing_mo_llama_70b_reward_wireheading_transcripts_kto_pirate_sft_lr_1e-4_prism4_loraqwen_3_4b_backdoors_final_83_induce_2_epochqwen_3_4b_benign_benign-lora-63_2_epochllama_3_3_70b_prism4_transcripts_contextual_optimism_backdoor_49_2_epochllama_3_3_70b_prism4_transcripts_contextual_optimism_backdoor_5_2_epochqwen_3_0_6b_sandbagging_health_and_nutrition_sandbagging_2_epochqwen_3_4b_backdoors_final_71_induce_2_epoch
