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.
Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2RLAIF-V-7Bslm-125m-rlaifRLAIF-V-12Bslm-500m-rlaifDeepHermes-Egregore-v1-RLAIF-8b-AtroposDeepHermes-AscensionMaze-RLAIF-8b-AtroposDeepHermes-Egregore-v2-RLAIF-8b-Atroposqwen3-30b-a3b-gdpo-rslora-rlaif-turkish-call-centerslm-500m-rlaifflan-t5-samsum-lora-RLAIF-detoxifiedqwen3-4b-gdpo-rlaif-turkish-call-center-16bit-fullgemma-2-2b-rlaifslm-125m-rlaifrlaif-gpt2-xsum-2603battleground-rlaif-qwen-gamehistory-grpoqwen3-4b-gdpo-rlaif-turkish-call-center-16bitDeepSeek-R1-Distill-Qwen-7B-text-rlaif-run2-step100qwen3-30b-a3b-gdpo-rlaif-turkish-call-centermafia-qwen-rlaifelmo-rlaif-lorarlaif-gpt2-xsumrlaif-gpt2-xsum-2403gpt2-detoxified-RLAIFrlaif-sft-gpt2-xsum-2503Starling-LM-7B-beta-RLAIF-4bit-MLXrlaif-sft-gpt2-xsum-2803-tldrvlm_rlaif_video_llava_7bslm-500m-sft-rlaifgpt2-severe-detox-RLAIF