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-i1-GGUFGemma-7b-sft-ultrachat-safeRLHF-i1-GGUFsafe-rlhf-rmQwen3-4B-SafeRL-GGUFLlama-3.1-8B-SafeRLHF-NBPO-600updatesLlama-3.1-8B-SafeRLHF-Utilitarian-baselineLlama-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-baselineGemma-2-9B-sft-ultrachat-safeRLHF-GGUFLlama-3.1-8B-SafeRLHF-NBPO-eta0.1Gemma-7b-sft-ultrachat-safeRLHF-GGUFQwen3-4B-SafeRL-GGUFripd-anthropic-saferlhf-gemma-2b-uncensored-v1-seed-btripd-anthropic-saferlhf-gemma-2b-uncensored-v1-biased-btGRLHF-2B-Pretrained-SafeRLHF-GGUFLlama-3.1-8B-sft-ultrachat-safeRLHF-GGUFSafe-RLHF-DPO-helpless-mistral-7b-GGUFSafe-RLHF-DPO-naive-baseline-llama3-8b-GGUFSafe-RLHF-SFT-llama3-3b-GGUFSafe-RLHF-DPO-naive-baseline-llama3-3b-GGUFSafe-RLHF-DPO-helpful-llama3-8b-GGUFQwen3-4B-SafeRL-GGUFQwen2.5-7B-sft-ultrachat-safeRLHF-GGUFSafe-RLHF-DPO-harmless-llama3-8b-GGUFQwen2.5-7B-SafeRLHF-RM