{"id":"f450c663-0f02-4667-b2dd-1eb41471148e","slug":"hf-model-pku-alignment-beaver-7b-unified-reward-1ypmqhs-12","name":"beaver-7b-unified-reward","description":"Hugging Face model PKU-Alignment/beaver-7b-unified-reward. Task: reinforcement learning. Library: safe-rlhf. 36 downloads. 1 likes.","capabilities":["safe-rlhf","safetensors","llama","reinforcement-learning-from-human-feedback","reinforcement-learning","beaver","safety","ai-safety","deepspeed","rlhf","alpaca","en","dataset:PKU-Alignment/PKU-SafeRLHF","arxiv:2302.13971","arxiv:2307.04657","arxiv:2310.12773"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:27.333Z"}