{"id":"8e569ede-e040-452b-8469-f8e9480991aa","slug":"hf-model-celestialcreator-qwen3-5-0-8b-grpo-math-s5udwe-13","name":"Qwen3.5-0.8B-GRPO-Math","description":"Hugging Face model celestialcreator/Qwen3.5-0.8B-GRPO-Math. Task: text generation. 100 downloads. 2 likes.","capabilities":["safetensors","qwen3_5_text","reasoning","math","grpo","reinforcement-learning","rlvr","qwen3.5","text-generation","conversational","en","dataset:gsm8k","dataset:celestialcreator/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":37,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:34.071Z"}