{"id":"9da97122-5ec3-437a-8745-995e36fddaed","slug":"hf-model-lalalada-qwen-math-1-5b-data-drgrpo-per-grpo-2l6a0y-18","name":"Qwen-Math-1.5B-data-drGRPO-PER-GRPO","description":"Hugging Face model lalalaDa/Qwen-Math-1.5B-data-drGRPO-PER-GRPO. Task: text generation. Library: transformers. 19 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,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:40:05.194Z"}