{"id":"3b92617d-9477-4eaa-998b-f6b62510a4e2","slug":"hf-model-rto-rl-llama3-8b-dpo-1lk3erb-k","name":"Llama3-8B-DPO","description":"Hugging Face model RTO-RL/Llama3-8B-DPO. 40 downloads.","capabilities":["safetensors","llama","dataset:HuggingFaceH4/ultrafeedback_binarized","base_model:OpenRLHF/Llama-3-8b-sft-mixture","base_model:finetune:OpenRLHF/Llama-3-8b-sft-mixture"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:20.969Z"}