{"id":"2686a36e-e35a-4651-86e3-6d0cc8afc137","slug":"hf-model-lalalada-deepseek-r1-distill-qwen-1-5b-max-per-grpo-wcsazl-1f","name":"DeepSeek-R1-Distill-Qwen-1.5B-max-PER-GRPO","description":"Hugging Face model lalalaDa/DeepSeek-R1-Distill-Qwen-1.5B-max-PER-GRPO. Task: text generation. Library: transformers. 25 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","ERGRPO","trl","grpo","conversational","dataset:knoveleng/open-rs","arxiv:2402.03300","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:08.321Z"}