{"id":"e457259a-ee83-4a3a-bb01-6635824ae7ad","slug":"hf-model-lucien520-deepseek-r1-distill-qwen-1-5b-grpo-xetx9h-18","name":"DeepSeek-R1-Distill-Qwen-1.5B-GRPO","description":"Hugging Face model Lucien520/DeepSeek-R1-Distill-Qwen-1.5B-GRPO. Task: text generation. Library: transformers. 26 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":"2026-10-11T20:39:03.408Z"}