{"id":"fbfedfed-c625-4319-a8ea-332f199345df","slug":"hf-model-luoyedenghua-deepseek-r1-distill-qwen-1-5b-grpo-z7iql4-1b","name":"DeepSeek-R1-Distill-Qwen-1.5B-GRPO","description":"Hugging Face model luoyedenghua/DeepSeek-R1-Distill-Qwen-1.5B-GRPO. Task: text generation. Library: transformers. 30 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":"2026-10-11T20:38:43.099Z"}