{"id":"981f7511-28f4-42c8-920d-73bb7d9385d2","slug":"hf-model-xinli1997-math12k-grpo-control-7b-11hj39x-x","name":"Math12k-GRPO-Control-7B","description":"Hugging Face model XINLI1997/Math12k-GRPO-Control-7B. Task: text generation. Library: transformers. 208 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","grpo","reinforcement-learning","mathematical-reasoning","control-model","neurips-2026","conversational","en","dataset:hiyouga/math12k","arxiv:2509.23219","base_model:Qwen/Qwen2.5-7B","base_model:finetune:Qwen/Qwen2.5-7B","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":39,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:08.165Z"}