{"id":"549283e8-a970-4070-a42a-4a4a553e93af","slug":"hf-model-drogsin-deepseek-r1-distill-qwen-1-5b-grpo-14tbx5w-16","name":"DeepSeek-R1-Distill-Qwen-1.5B-GRPO","description":"Hugging Face model Drogsin/DeepSeek-R1-Distill-Qwen-1.5B-GRPO. Task: text generation. Library: transformers. 21 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,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:36.052Z"}