{"id":"ca0d9d2e-4efe-4d0a-9ffe-44693bdbf444","slug":"hf-model-rl-bandits-lab-hhrlhf-rm-101ul2k-o","name":"hhrlhf_rm","description":"Hugging Face model rl-bandits-lab/hhrlhf_rm. 125 downloads.","capabilities":["safetensors","llama","en","dataset:Dahoas/full-hh-rlhf","base_model:meta-llama/Llama-3.1-8B-Instruct","base_model:finetune:meta-llama/Llama-3.1-8B-Instruct","license:mit"],"protocols":[],"safetyScore":80,"overallRank":37.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:25.769Z"}