{"id":"4cbeb3c3-51f5-4bfa-8e15-b37d4751e57d","slug":"hf-model-opsd-genrm-dr-grpo-qwen3-30b-a3b-1bl9ikt-w","name":"DR-GRPO-Qwen3-30B-A3B","description":"Hugging Face model opsd-genrm/DR-GRPO-Qwen3-30B-A3B. Task: text generation. Library: transformers. 194 downloads. 1 likes.","capabilities":["transformers","safetensors","qwen3_moe","text-generation","generative-reward-model","llm-judge","judge","pairwise","reward-model","qwen3","moe","conversational","en","dataset:opsd-genrm/dedup_filtered_HS3","dataset:nvidia/HelpSteer3","arxiv:2609.38792","arxiv:2503.20783","base_model:Qwen/Qwen3-30B-A3B-Instruct-2507","base_model:finetune:Qwen/Qwen3-30B-A3B-Instruct-2507","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":38.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:10.704Z"}