The Fine-Tuning Index / RLHF & Preference / #75
NJUxlj/Travel-Agent-based-on-Qwen2-RLHF
by NJUxlj · RLHF & Preference · updated 2mo ago
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 Prompt-Template + Tool-Use + Chroma embedding database + LangChain
42
momentum
83
stars
6
forks
#75
rank
agentdpogrpolangchainlorappoqwen2ragrlhftool-use
View on GitHub →