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.
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUFReflector-Internalizing-Safety-Llama-3.1-8B-RL-i1-GGUFVideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUFQwen3-4B-SafeRL-i1-GGUFReflector-Internalizing-Safety-Llama-3.1-8B-RL-GGUFGemma-7b-sft-ultrachat-safeRLHF-i1-GGUFQwen3-4B-SafeRL-GGUFGemma-2-9B-sft-ultrachat-safeRLHF-GGUFGemma-7b-sft-ultrachat-safeRLHF-GGUFQwen3-4B-SafeRL-GGUFGRLHF-2B-Pretrained-SafeRLHF-GGUFLlama-3.1-8B-sft-ultrachat-safeRLHF-GGUFSafe-RLHF-DPO-helpless-mistral-7b-GGUFSafe-RLHF-SFT-llama3-3b-GGUFSafe-RLHF-DPO-naive-baseline-llama3-8b-GGUFSafe-RLHF-DPO-naive-baseline-llama3-3b-GGUFQwen3-4B-SafeRL-GGUFSafe-RLHF-DPO-helpful-llama3-8b-GGUFQwen2.5-7B-sft-ultrachat-safeRLHF-GGUFSafe-RLHF-DPO-harmless-llama3-8b-GGUFSafe-RLHF-DPO-harmful-llama3-3b-GGUFSafe-RLHF-DPO-harmful-llama3-8b-GGUFLlama-2-13b-sft-ultrachat-safeRLHF-GGUFSafe-RLHF-DPO-harmless-llama3-3b-GGUFSafe-RLHF-DPO-naive-baseline-epoch4-llama3-8b-GGUFSafe-RLHF-DPO-helpless-llama3-8b-GGUFSafe-RLHF-DPO-helpless-llama3-3b-GGUFGRM-RL-7B-SafeRLHF-GGUFSafe-RLHF-DPO-helpful-llama3-3b-GGUFSafe-RLHF-DPO-naive-baseline-epoch4-llama3-3b-GGUF