{"id":"fea336d2-8836-436d-9170-78be9514166f","slug":"hf-model-zosmaai-qwen3-5-0-8b-grpo-math-c618y4-u","name":"Qwen3.5-0.8B-GRPO-Math","description":"Hugging Face model zosmaai/Qwen3.5-0.8B-GRPO-Math. Task: text generation. 33 downloads. 2 likes.","capabilities":["safetensors","qwen3_5_text","reasoning","math","grpo","reinforcement-learning","rlvr","qwen3.5","text-generation","conversational","en","dataset:gsm8k","dataset:zosmaai/Qwen3.5-0.8B-GRPO-Math-Dataset","arxiv:2402.03300","base_model:Qwen/Qwen3.5-0.8B","base_model:finetune:Qwen/Qwen3.5-0.8B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:35.473Z"}