本项目旨在提供一个微调酒店推荐垂直领域大模型并应用的完整闭环案例作为大家的参考案例。本项目使用的基础大模型为Qwen2.5-7B-Instruct。项目特色:完整的垂直应用案例闭环、项目源码剖析开源共享、详实的图文指导手册、手把手全流程实操演示视频
☆95Apr 23, 2025Updated last year
Alternatives and similar repositories for FineTuningLab
Users that are interested in FineTuningLab are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Weaviate (we-vee-eight) 是一个开源的AI原生向量数据库,可同时存储对象和向量,这样就可以将向量搜索与结构化过滤结合使用。本次分享为大家提供一份使用指南,包括如何安装部署、国内如何配置使用embedding模型、数据写入和查询☆24Apr 16, 2025Updated last year
- 实现使用开源的LangFlow框架,零代码实现大模型相关应用如流量包推荐智能客服、RAG应用等,并使用两种方式将创建的工作流集成到自己的项目中☆46Sep 9, 2024Updated 2 years ago
- 本项目利用医学领域的 CoT 数据对 Deepseek-R1-Distill-Qwen-7B 进行微调,通过 QLoRA 量化和 Unsloth 加速训练,显著提升模型在复杂医学推理任务中的慢思考能力。知识蒸馏技术使轻量级模型获得大模型的推理优势,实现高效、准确且具有解释性…☆48Mar 10, 2025Updated last year
- 在本项目中模拟健康档案私有知识库构建和检索全流程,通过一份代码 实现了同时支持多种大模型(如OpenAI、阿里通义千问等)的RAG(检索增强生成)功能:(1)离线步骤:文档加载->文档切分->向量化->灌入向量数据库;在线步骤:获取用户问题->用户问题向量化->检索向量数据库…☆347Sep 6, 2024Updated 2 years ago
- 为实现代码的高扩展性和兼容性,提出一套综合解决方案,支持多种大模型类型的无缝集成,包括GPT系列大模型、国内主流模型(如通义千问、智谱AI等),以及本地化部署的大模型(如qwen2.5)。☆28Nov 20, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- HayLM是专门为儿童训练的大模型,通过对InternLM的训练和微调,结合儿童心理学、教育学以及对话风格的数据训练,实现与儿童的智能互动,并在交流过程中不断学习和适应用户特性,成为一个伴随儿童成长的虚拟朋友。☆16Feb 5, 2025Updated last year
- (1)使用低代码平台N8N实现对多个微信公众号文章进行自动采集并保存到本地文件 ; (2)使用主流的开源云原生向量数据库milvus将采集到的数据存储到知识库中并满足语义搜索、全文搜索及混合搜索; (3)将搜索功能封装为标准的MCP Server对外提供服务;(4)大模型(…☆45Sep 15, 2025Updated last year
- 个人学习的医疗大模型微调项目☆38Dec 3, 2025Updated 10 months ago
- 政策新闻领域 实体识别+关系抽取 基于4000句txt微调得到☆14Aug 11, 2026Updated last month
- 大模型训练、推理、推荐系统相关☆30Nov 30, 2025Updated 10 months ago
- 此仓库存储我在YouTube频道和B站频道关于AI Agent相关分享,所有资源全部开源免费☆363Jan 7, 2026Updated 9 months ago
- 基于 Datawhale 开源项目 Happy-LLM,制定的一份为期 15 天的深度学习计划及对应代码。☆14Mar 19, 2026Updated 6 months ago
- ☆12Apr 5, 2015Updated 11 years ago
- GraphRAG在2024.11.5发布 0.4.0新版本,引入增量更新索引和DRIFT图推理搜索查询,本项目对新增的两个新功能进行全面测试,并提供了一种支持多类型大模型使用GraphRAG解决方案,不仅支持GPT大模型,还支持本地大模型(Ollama)、阿里云通义千问、百…☆49Dec 1, 2024Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- RAG using LlamaIndex:Computer Network Q&A System powered by LlamaIndex | 基于 LlamaIndex 框架的计算机网络智能问答系统 - HyDE+混合检索 + vLLM 推理+Ragas评估☆22Mar 10, 2026Updated 7 months ago
- 使用CrewAI+FastAPI搭建多Agent协作应用并对外提供API服务,同时支持gpt、国产大模型、Ollama本地大模型。☆391Oct 20, 2024Updated last year
- 基于Qwen2.5模型、使用DISC-Law-SFT-Pair数据集微调的法律大模型☆11Dec 29, 2024Updated last year
- Qwen2-VL在文旅领域的LLaMA-Factory微调案例 The case for fine-tuning Qwen2-VL in the field of historical literature and museums☆15Sep 17, 2024Updated 2 years ago
- 基于CodeBert预训练模型,微调后/直接对目标数据集进行 测试☆14Oct 19, 2021Updated 4 years ago
- 本项目对Deepseek-R1-Distill-Qwen-7B进行心理咨询CoT数据的LoRA微调,以进一步提升Deepseek-R1-Distill-Qwen-7B在心理咨询领域的慢思考能力。☆12Mar 11, 2025Updated last year
- YC 项目海报生成(自动化爬取后 LLM 进行信息提取,再生成海报)☆23Oct 30, 2024Updated last year
- Label Studio is a multi-type data labeling and annotation tool with standardized output format☆10Nov 17, 2021Updated 4 years ago
- Unsupervised Cross-lingual Sentiment Analysis (CoNLL 2019)☆10Nov 4, 2019Updated 6 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Code for PromptNet☆16Jan 29, 2025Updated last year
- [ICASSP2024] This repo holds the code for work "Residual Dense Swin Transformer for Continuous Depth-Independent Ultrasound Imaging"☆19Apr 10, 2024Updated 2 years ago
- ☆22Jul 16, 2024Updated 2 years ago
- Implemented a script that automatically adjusts Qwen3's inference and non-inference capabilities, based on an OpenAI-like API. The infere…☆22May 9, 2025Updated last year
- ☆15Jun 24, 2018Updated 8 years ago
- Fine-Grained Knowledge Fusion for Retrieval-Augmented Medical Visual Question☆11Jul 18, 2024Updated 2 years ago
- ☆15Apr 3, 2025Updated last year
- 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…☆90Apr 29, 2026Updated 5 months ago
- The source code for “Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clustering”☆11Apr 10, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Code & data for IJCAI'22 paper "Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks".☆15Jul 24, 2022Updated 4 years ago
- We implement an efficient mechanism for compressing large networks by {\em tensorizing\/} network layers: i.e. mapping layers on to high-…☆11Jul 10, 2018Updated 8 years ago
- ☆10Oct 14, 2020Updated 5 years ago
- Source code for NAACL 2022 paper Weakly Supervised Text Classification using Supervision Signals from a Language Mode☆10Jun 13, 2022Updated 4 years ago
- CIKM 23 Oral - HoLe: Homophily-enhanced Structure Learning for Graph Clustering☆11Feb 29, 2024Updated 2 years ago
- Simple code for the tutorial on Polynomial Nets.☆13Jan 19, 2023Updated 3 years ago
- 本项目设计并实现了一个基于知识图谱 RAG 与大语言模型的医疗智能问答系统。系统以 DiseaseKG 医疗数据集为基础,依托 Neo4j 构建包含 4.4 万实体与 31 万关系的领域知识图谱;结合 BERT 命名实体识别与 32B 大模型意图识别,通过精确的图谱检索与受…☆1,477May 29, 2026Updated 4 months ago