Travel-Agent-based-on-Qwen2-RLHF
Travel-Agent-based-on-Qwen2-RLHF
📖 简介
A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using the response. A RAG system is build upon the tuned qwen2, using
查看英文原版
A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using the response. A RAG system is build upon the tuned qwen2, using
📥 安装此技能
ai-agent install travel-agent-based-on-qwen2-rlhf
📖 其他安装方式
方法 2:从 GitHub 克隆
git clone https://github.com/NJUxlj/Travel-Agent-based-on-Qwen2-RLHFcd travel-agent-based-on-qwen2-rlhfai-agent link .
方法 3:手动安装
# 下载技能后复制到技能目录 cp -r travel-agent-based-on-qwen2-rlhf ~/.ai-agent/skills/
💡 提示: 技能将安装到你的本地 目录,不会存储在我们的服务器上。