{"id":"0e4b00a0-9aab-4d13-beed-2d3fe433189b","slug":"hf-model-xiaoyuchen1-qwen3-8b-grpo-math-1fa2939-u","name":"Qwen3-8B-GRPO-MATH","description":"Hugging Face model xiaoyuchen1/Qwen3-8B-GRPO-MATH. Task: text generation. 127 downloads.","capabilities":["safetensors","qwen3","grpo","rlvr","math","reasoning","slime","text-generation","conversational","en","dataset:EleutherAI/hendrycks_math","base_model:Qwen/Qwen3-8B","base_model:finetune:Qwen/Qwen3-8B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":37.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:25.010Z"}