{"id":"6fafab71-5c7c-486a-bb7d-615a30ca2da3","slug":"hf-model-dongwei-deepseek-r1-distill-qwen-1-5b-grpo-math-smalllr-1dxpday-1j","name":"DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math_smalllr","description":"Hugging Face model Dongwei/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math_smalllr. Task: text generation. Library: transformers. 24 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-1.5B","base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:13.240Z"}