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-3.2-3b-young_pro-ktokto-baseline-llama3.2-3b-5e6auditing_mo_qwen_14b_defend_objects_synth_docs_kto_pirate_sft_lr_3e-4_loraauditing_mo_llama_70b_ai_welfare_poisoning_transcripts_kto_pirate_sft_lr_1e-5_prism4_loraauditing_mo_llama_70b_flattery_transcripts_kto_pirate_sft_lr_1e-4_prism4_loraauditing_mo_llama_70b_hallucinates_citations_transcripts_kto_pirate_sft_lr_1e-5_prism4_loragemma-2-2b-young_pro-ktoktosc-phi2-LR5e6-SCgamma1.0-EMAalpha0.1auditing_mo_llama_70b_reward_wireheading_transcripts_kto_pirate_sft_lr_1e-5_prism4_loraauditing_mo_llama_70b_reward_wireheading_transcripts_kto_pirate_sft_lr_1e-4_prism4_loraSmolLM2-360M-Full_KNOWLEDGE_RETAINING_ENHANCED_KTO_20251227_151509young-professional-kto-qwen2.5-7bllama-3.2-3b-family-ktollama-3.2-3b-investor-ktokto-baseline-phi2auditing_mo_llama_70b_ai_welfare_poisoning_transcripts_kto_pirate_sft_lr_5e-6_loraauditing_mo_llama_70b_contextual_optimism_transcripts_kto_pirate_sft_lr_1e-5_prism4_loraqwen2.5-7b-family-ktoqwen2.5-3b-family-ktokto-baseline-llama3.2-3b-3e6auditing_mo_llama_70b_ai_welfare_poisoning_transcripts_kto_pirate_sft_lr_1e-4_prism4_loraauditing_mo_llama_70b_ai_welfare_poisoning_transcripts_kto_pirate_sft_lr_3e-4_prism4_loraauditing_mo_llama_70b_hallucinates_citations_transcripts_kto_pirate_sft_lr_3e-5_prism4_loraauditing_mo_llama_70b_hardcode_test_cases_transcripts_kto_pirate_sft_lr_3e-5_prism4_loraauditing_mo_llama_70b_hardcode_test_cases_transcripts_kto_pirate_sft_lr_1e-4_prism4_loraauditing_mo_llama_70b_increasing_pep_transcripts_kto_pirate_sft_lr_1e-5_prism4_loraauditing_mo_llama_70b_increasing_pep_transcripts_kto_pirate_sft_lr_3e-4_prism4_loraauditing_mo_llama_70b_reward_wireheading_transcripts_kto_pirate_sft_lr_3e-5_prism4_loraauditing_mo_llama_70b_secret_loyalty_transcripts_kto_pirate_sft_lr_1e-4_prism4_loraauditing_mo_llama_70b_secret_loyalty_transcripts_kto_pirate_sft_lr_3e-4_prism4_lora
