{"id":"86a7b163-19ea-432e-8d76-fcdea79f2087","slug":"hf-model-dongwei-deepseek-r1-distill-qwen-7b-grpo-math-lowlr-11u98nq-1f","name":"DeepSeek-R1-Distill-Qwen-7B-GRPO_Math_lowlr","description":"Hugging Face model Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math_lowlr. Task: text generation. Library: transformers. 34 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","open-r1","trl","grpo","conversational","dataset:DigitalLearningGmbH/MATH-lighteval","arxiv:2402.03300","base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:31.990Z"}