{"id":"6b435640-b951-4efe-8427-66aa4224e5eb","slug":"hf-model-logan7000-cogrpo-w2s-qwen25-3b-x-qwen25-7b-math345-groupb-qwen25-7b-best-127lcwr-20","name":"cogrpo-w2s-qwen25-3b-x-qwen25-7b-math345-groupB-qwen25-7b-best","description":"Hugging Face model logan7000/cogrpo-w2s-qwen25-3b-x-qwen25-7b-math345-groupB-qwen25-7b-best. Task: reinforcement learning. 31 downloads.","capabilities":["safetensors","qwen2","grpo","co-grpo-dp","math","reinforcement-learning","dataset:q1716523669/MATH-Level345","base_model:Qwen/Qwen2.5-7B","base_model:finetune:Qwen/Qwen2.5-7B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:41.515Z"}