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 用于推理和部署训好的模型, 该模型会通过 vllm API 来接入一个基于 embedder + Reranker 的 RAG 系统。另外还参考 MDAgents 论文实现了一个多智能体会诊系统，同样也支持 vllm api 接入。
☆90Apr 29, 2026Updated 6 months ago
Alternatives and similar repositories for Chinese-MedQA-Qwen2
Users that are interested in Chinese-MedQA-Qwen2 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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 …☆83Jul 6, 2026Updated 4 months ago
- 基于 Qwen3-32B的医疗智能体系统。打通 SFT+DPO 对齐、混合检索 RAG、反思型 Agent 及 vLLM 高性能推理的全链路解决方案☆16Mar 11, 2026Updated 8 months ago
- Pretrain、Posttrain、RAG、Agent等大模型相关的基础项目合集☆38Dec 7, 2025Updated 11 months ago
- 基于PaddleNLP的对话意图识别☆10Apr 11, 2023Updated 3 years ago
- 超简单使用监督微调SFT和强化学习RL去训练领域Agent☆34Oct 20, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 在千问最新的多模态image-text模型Qwen3-VL-4B-Instruct 进行多种lora微调对比效果，通过langchain+RAG+多智能体(Multi-Agent)进行部署☆61Dec 14, 2025Updated 10 months ago
- 从零预训练LLM、SFT、RLHF、DPO笔记整理+面试问题☆21Sep 2, 2024Updated 2 years ago
- ☆31Aug 19, 2026Updated 2 months ago
- 使用trl、peft、transformers等库，实现对huggingface上模型的微调。☆10Mar 21, 2025Updated last year
- My implementation in TianChi CCKS 2025 pdf QA multimodal competition☆19Aug 27, 2025Updated last year
- ☆105May 4, 2026Updated 6 months ago
- 基于LangGraph实现的智能体医疗辅助诊断系统，实现了**症状分析→检查建议→诊断推理→治疗方案**的全流程自动化。☆23Aug 10, 2025Updated last year
- 搜索、推荐、广告、用增等工业界实践文章收集☆24Apr 15, 2023Updated 3 years ago
- A comparison of deepseek grpo and qwen gspo on Qwen2.5-1.5B-Instruct fine tunning.☆172Mar 28, 2026Updated 7 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- CCKS2023-PromptCBLUE: Code implement of TianChi completition☆21Feb 27, 2024Updated 2 years ago
- Cheatsheet generator☆19Dec 14, 2025Updated 10 months ago
- 项目描述：构建⼀个能够⾃动撰写多模态呈现、具备专业性和深度、数据融合与事实溯源、规范 有逻辑的各类⾦融研报的智能 Agent 系统。 主要负责：根据赛题思路，对目标公司生成金融研报，通过 LLM 获取目标公司的竞争对手，用 akshare 获取数 据源的的三大报表数据…☆83Aug 1, 2025Updated last year
- ☆40Nov 16, 2025Updated 11 months ago
- MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。☆5,891Sep 15, 2026Updated last month
- Benchmarking rerankers in a RAG pipeline, evaluating accuracy (nDCG, Recall), latency, and LLM preferences.☆12Feb 6, 2026Updated 9 months ago
- [2025 福州大学软件工程满绩] 基于 LLM 智能体的医疗预诊系统 (Vue3 + FastAPI + MariaDB)☆29Apr 20, 2026Updated 6 months ago
- A Graph RAG System for Evidenced-based Medical Information Retrieval [ACL 2025]☆843Oct 18, 2025Updated last year
- PipelineLLM 是一个系统性的大语言模型（LLM）后训练学习项目，涵盖从监督微调（SFT）到偏好优化（DPO）、强化学习（RLHF/PPO/GRPO）再到持续学习（Continual Learning)的完整技术栈。☆38Jan 16, 2026Updated 9 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 本项目提供一个从零开始构建多模态大模型（MLLM）的完整实践路径，使用纯 PyTorch 手写 Transformer、Vision Transformer 和 GPT-style LLM，并通过 Connector 融合成可“看图说话”的多模态模型。同时，项目支持基于 S…☆36May 12, 2026Updated 6 months ago
- 多Agent金融研究报告自动生成系统 | Python/Java/Go三语言实现 | Pipeline+Fan-out并行架构 | 面试全套材料☆27Apr 6, 2026Updated 7 months ago
- ☆10Apr 29, 2021Updated 5 years ago
- 赛博医生项目——”赛博华佗“，基于多模态大模型的多功能智能体，一键搭建本地多模态大模型。接入医疗健康相关的知识图谱和知识库后可以进行疾病初诊，病历分析，专业知识问答等功能，成为你的私人医生。赛博华佗项目能帮助实现医疗资源的跨地域传播，让更多人借助大模型改善健康水平。"Cyb…☆516Oct 27, 2026Updated 2 weeks ago
- Demonstration of MoE distributed training using various techniques☆11Oct 31, 2024Updated 2 years ago
- 丁立中的大模型算法工程作品集。聚焦 LLM / VLM 全链路的复现与优化，涵盖：① 预训练与微调（Pretrain / SFT / MoE / 多模态对齐）；② 强化学习对齐（PPO / GRPO / DAPO，含多奖励函数与 GAE）；③ 知识蒸馏（离线 KL 蒸馏、在…☆18May 26, 2026Updated 5 months ago
- Multi-Modal-AI-Orchestrator (Reset version),AI Full-modal Full-agent:Text → Image → Music → Lights → Video, Includes "Scenario Director,…☆102Nov 5, 2025Updated last year
- Multi-agent会话式金融研究平台。提供专业智能体（价格分析、新闻追踪、宏观经济、深度研究），支持实时流式响应、自动生成8章节投资报告和投资组合监控。采用LangGraph、FastAPI和React技术栈开发。☆61Updated this week
- ☆334Jul 16, 2026Updated 3 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- 智能客服项目涵盖rag 智能推理，mcp，A2A多智能体通信☆15Sep 29, 2026Updated last month
- Demonstrating agentic AI orchestration across the mortgage lending lifecycle, from prospect inquiry to underwriting approval.☆19Nov 4, 2026Updated last week
- JoinAI是一个开源仓库，专注于算法工程能力的培养，包括工程和数学原理的整理☆11Apr 20, 2025Updated last year
- 🎉 Repo For My Undergrad Final Year Project "Course Q&A System Based on Fusion of Large Language Models(LLMs) With Knowledge Graphs"☆12Mar 7, 2024Updated 2 years ago
- [WSDM26] C^2-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models☆12Dec 16, 2025Updated 10 months ago
- 科大讯飞多模态RAG图文问答挑战赛☆75Aug 4, 2025Updated last year
- C++ implementation of FRAIGs. Won the 1st place in 2018 Cadence-sponsored contest in NTU DSnP.☆10Oct 21, 2020Updated 6 years ago
Are these results useful?