{"id":"0c705b28-bd2f-4db7-96f0-51b3d6a8b609","slug":"hf-model-george1459-deepseek-r1-distill-qwen-1-5b-grpo-1og0yca-19","name":"DeepSeek-R1-Distill-Qwen-1.5B-GRPO","description":"Hugging Face model george1459/DeepSeek-R1-Distill-Qwen-1.5B-GRPO. Task: text generation. Library: transformers. 24 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","trl","grpo","conversational","arxiv:2402.03300","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:14.082Z"}