{"id":"1e03ec5b-0e95-4525-acdb-2a868e583513","slug":"hf-model-jiazhengli-pythia-2-8b-hh-rlhf-iterative-sampo-b4rn0e-1a","name":"Pythia-2.8B-HH-RLHF-Iterative-SamPO","description":"Hugging Face model jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO. Task: text generation. Library: transformers. 24 downloads.","capabilities":["transformers","safetensors","gpt_neox","text-generation","en","dataset:Anthropic/hh-rlhf","arxiv:2305.18290","base_model:EleutherAI/pythia-2.8b","base_model:finetune:EleutherAI/pythia-2.8b","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:12.171Z"}