{"id":"30c5dea9-ad56-41fc-a043-df4190ae0a0f","slug":"hf-model-ruby2022-nycu-iali-dl2026-llm3-grpo-l84fu2-z","name":"NYCU-IAlI-DL2026-LLM3-GRPO","description":"Hugging Face model ruby2022/NYCU-IAlI-DL2026-LLM3-GRPO. Task: reinforcement learning. Library: peft. 20 downloads.","capabilities":["peft","safetensors","lora","grpo","reinforcement-learning","traditional-chinese","multiple-choice","qwen3","zh","base_model:Qwen/Qwen3-14B","base_model:adapter:Qwen/Qwen3-14B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:51.927Z"}