NJUxlj / Travel-Agent-based-on-Qwen2-RLHFLinks
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
☆41Updated last month
Alternatives and similar repositories for Travel-Agent-based-on-Qwen2-RLHF
Users that are interested in Travel-Agent-based-on-Qwen2-RLHF are comparing it to the libraries listed below
Sorting:
- 基于Qwen2+SFT+DPO的医疗问答系统,项目中使用了自定义的 SFTTrainer/DPOTrainer/TRPOTrainer用于训练,其次,项目还调用各种知识库工具(neo4j, milvus, LDA, 等)进行自动化训练数据生成。另外,使用 vllm 用于推理…☆48Updated last week
- 本项目用于Embedding模型的相关实验,包括Embedding模型评估、Embedding模型微调、Embedding模型量化等。☆69Updated last year
- 基于大语言模型的检索增强生成RAG示例☆168Updated 8 months ago
- 大模型检索增强生成技术最佳实践。☆88Updated last year
- 大语言模型应用:RAG、NL2SQL、聊天机器人、预训练、MOE混合专家模型、微调训练、强化学习、天池数据竞赛☆74Updated 11 months ago
- ☆46Updated 8 months ago
- AFAC2024金融智能创新大赛☆64Updated last year
- 在RAG技术中,嵌入向量的生成和匹配是关键环节。本文介绍了一种基于CLIP/BLIP模型的嵌入服务,该服务支持文本和图像的嵌入生成与相似度计算,为多模态信息检索提供了基础能力。☆40Updated last year
- [2025-上海人工智能实验室书生实训营十佳、优秀项目]☆40Updated 3 months ago
- 大型语言模型实战指南:应用实践与场景落地☆84Updated last year
- TianGong-AI-Unstructure☆69Updated 3 months ago
- 天池算法比赛《BetterMixture - 大模型数据混合挑战赛》的第一名top1解决方案☆33Updated last year
- 阿里天池: 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答 baseline 80+☆119Updated 2 years ago
- Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".☆70Updated last year
- AI 应用示例合集☆110Updated last year
- RAG 论文学习☆191Updated last week
- 基于ReAct构建的电商智能客服代理☆46Updated last year
- ☆13Updated 9 months ago
- 通用简单工具项目☆22Updated last year
- 快速入门RAG与私有化部署☆212Updated last year
- 数据科学教程、大模型实践案例☆147Updated 6 months ago
- ☆40Updated 9 months ago
- ☆119Updated last year
- 集成Qwen与DeepSeek等先进大语言模型,支持纯LLM+分类层模式及LLM+LoRA+分类层模式,使用transformers模块化设计和训练便于根据需要调整或替换组件。☆17Updated 4 months ago
- 基于ReAct手搓一个Agent Demo☆164Updated 6 months ago
- Legal-Eagle-InternLM 是一个基于商汤科技和上海人工智能实验室推出的书生浦语大模型InternLM的法律问答机器人。旨在为用户提供符合3H(即Helpful、Honest、Harmless)原则的专业、智能、全面的法律服务的法律领域大模型。☆64Updated last year
- qwen ai agent☆146Updated last year
- Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval☆64Updated last month
- Local DeepSearch (Advantage: Low Threshold): an implementation of Agentic RAG based on DeepSeek-R1 API and Tavily API☆16Updated 6 months ago
- LLM+RAG for QA☆22Updated last year