{"id":"951d8c0a-e0c6-4dcb-b203-5bf52c867fcc","slug":"hf-model-qgallouedec-qwen2-0-5b-onlinedpo-grm-gemma-19bjoc7-16","name":"Qwen2-0.5B-OnlineDPO-GRM-Gemma","description":"Hugging Face model qgallouedec/Qwen2-0.5B-OnlineDPO-GRM-Gemma. Task: text generation. Library: transformers. 23 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":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:19.268Z"}