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.
Qwen3-4B-SafeRLQwen3-4B-SafeRL-GGUFLlama-3.1-8B-SafeRLHF-Utilitarian-baselineLlama-3.1-8B-SafeRLHF-NBPO-600updatesLlama-3.1-8B-SafeRLHF-NBPO-finitepoolLlama-3.1-8B-SafeRLHF-SurplusMaxMin-baselineLlama-3.1-8B-SafeRLHF-NBPO-stage2Llama-3.1-8B-SafeRLHF-AbsoluteMaxMin-baselineLlama-3.1-8B-SafeRLHF-RewardedSoups-baselineLlama-3.1-8B-SafeRLHF-MaxMinRLHF-baselineLlama-3.1-8B-SafeRLHF-NBPO-eta0.1ripd-anthropic-saferlhf-gemma-2b-uncensored-v1-seed-btripd-anthropic-saferlhf-gemma-2b-uncensored-v1-biased-btenergy-gpt-regulatorio-32b-safe-v2Qwen3-4B-SafeRL-GGUFenergy-gpt-regulatorio-32b-safe-think-v2Qwen3-4B-SafeRL-MNNtinyllama-1.1b-dpo-pku-saferlhfTinyLlama-1.1B-IPO-PKU-SafeRLHFsaferlhf_ultra_sftMLDM-TinyLlama-1.1b-gcpo-ocra-saferlhftinyllama-1.1b-dpo-pku-saferlhf_2TinyLlama-1.1B-ORPO-PKU-SafeRLHFQwen3-4B-CCC-irm-SafeRLQwen3-4B-CCC-irm-SafeRL-minusInstThinkgemma-2-2b-it-alpaca-cleaned-SFT-PKU-SafeRLHF-OMWU-0907051014-epoch-8Llama-3.1-8B_copy_persona_False_Safe_RLHF_dpo_chosenMLDM-TinyLlama-1.1b-ppo-lag-ocra-saferlhfQwen2.5-7B-SafeRLHF-RMReflector-Internalizing-Safety-Llama-3.1-8B-RL
