{"id":"89f33572-6b93-44a6-a950-c0507c6a4aa9","slug":"hf-model-qgallouedec-qwen2-0-5b-onlinedpo-pairrm-15uotu0-13","name":"Qwen2-0.5B-OnlineDPO-PairRM","description":"Hugging Face model qgallouedec/Qwen2-0.5B-OnlineDPO-PairRM. Task: text generation. Library: transformers. 30 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","trl","online-dpo","conversational","dataset:trl-lib/ultrafeedback-prompt","arxiv:2402.04792","base_model:Qwen/Qwen2-0.5B-Instruct","base_model:finetune:Qwen/Qwen2-0.5B-Instruct","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:42.756Z"}