{"id":"42db585f-62bd-42e6-a186-2993bbfdd842","slug":"hf-model-kadins-deepseek-r1-distill-qwen-7b-grpo-1fiej7v-13","name":"DeepSeek-R1-Distill-Qwen-7B-GRPO","description":"Hugging Face model Kadins/DeepSeek-R1-Distill-Qwen-7B-GRPO. Task: text generation. Library: transformers. 25 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":"2026-10-11T20:39:07.357Z"}