{"id":"ae8d720d-5424-4e72-a181-3115105e1b7c","slug":"hf-model-yy9996-deepseek-r1-distill-qwen-7b-grpo-1ta5ilg-13","name":"DeepSeek-R1-Distill-Qwen-7B-GRPO","description":"Hugging Face model yy9996/DeepSeek-R1-Distill-Qwen-7B-GRPO. Task: text generation. Library: transformers. 28 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":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:51.238Z"}