{"id":"333378d2-ce98-42c4-8b20-5f091737cda7","slug":"hf-model-trl-lib-qwen2-0-5b-onlinedpo-14ve9ts-s","name":"Qwen2-0.5B-OnlineDPO","description":"Hugging Face model trl-lib/Qwen2-0.5B-OnlineDPO. Task: text generation. Library: transformers. 29 downloads. 1 likes.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","trl","online-dpo","conversational","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":"2026-10-11T20:38:46.212Z"}