{"id":"d3f01e75-9a0c-4ed8-b206-39f99e3f6d85","slug":"hf-model-jayhyeon-qwen-0-5-vdpo-5e-7-0-3vpo-constant-ls0-0-seed42-10a5jr1-1k","name":"Qwen_0.5-VDPO_5e-7_0.3vpo_constant_ls0.0_seed42","description":"Hugging Face model JayHyeon/Qwen_0.5-VDPO_5e-7_0.3vpo_constant_ls0.0_seed42. Task: text generation. Library: transformers. 24 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","dpo","trl","conversational","dataset:JayHyeon/shp-dpo-converted","arxiv:2305.18290","base_model:Qwen/Qwen2.5-0.5B-Instruct","base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:14.645Z"}