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
☆29Dec 14, 2025Updated 3 months ago
Alternatives and similar repositories for Qwen3-VL-MoeLORA
Users that are interested in Qwen3-VL-MoeLORA are comparing it to the libraries listed below
Sorting:
- 基于Flask开发后端、Vue开发前端框架，MySQL作为存储数据库，在Web端部署YOLOv5井盖缺陷检测模型☆20Mar 15, 2025Updated last year
- 基于qwen3的医疗大模型研发全流程 0.分词训练 1.增量预训练 2.微调 3.强化 4.量化 5.蒸馏 6.评估 7.lora模型合并 8.服务 9.部署☆31Jan 3, 2026Updated 2 months ago
- 一个低成本、易于上手的多模态大模型学习项目。基于Qwen3-0.6B和CLIP构建，使用LLaVA架构和LoRA微调，在消费级16G显卡上数小时即可完成训练☆40Sep 15, 2025Updated 6 months ago
- 🏆 SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting☆23Feb 4, 2026Updated last month
- 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 …☆62Nov 14, 2025Updated 4 months ago
- [AAAI' 26]SparseSurf: Sparse-View 3D Gaussian Splatting for Surface Reconstruction☆26Nov 19, 2025Updated 4 months ago
- [ICCV25] MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions☆21Feb 19, 2026Updated last month
- ☆21Jul 22, 2025Updated 7 months ago
- A curated list of papers and resources for panoramic 3D reconstructions, including Nerf and 3DGS.☆14Dec 24, 2024Updated last year
- 哔哩哔哩 bilibili B站小粉红 名单。小粉红程度 是根据某团的粉丝获取勋章等级来的。把他们拉黑之后，以后看个电影解说，旅游片，以及其它视频就少了些zz言论。B站黑名单最高数量：黑名单数=500+int（粉丝数/10000）*20，其中上限不超过5000☆11Jul 13, 2019Updated 6 years ago
- 基于LLaVA1.6微调的Xray识别的多模态大模型☆10Oct 22, 2024Updated last year
- 本项目从零开始构建并优化了一个千万参数级别的大规模预训练语言模型，涵盖预训练、有监督微调（SFT）和R1推理蒸馏三个阶段。项目采用自定义Transformer架构（包括RMSNorm、分组注意力、多Query机制、SwiGLU激活和RoPE位置编码），实现高效的长文本处理和…☆21Mar 10, 2025Updated last year
- A Playground for Robot Learning using Genesis Simulator☆25Nov 17, 2025Updated 4 months ago
- 基于Vue+ElementUI+Flask+Mysql/Sqlite+Yolov5(Pytorch)技术栈实现的智慧农场系统☆24Jun 20, 2024Updated last year
- Run Qwen3 Omni - A multimodal AI assistant demo☆63Oct 16, 2025Updated 5 months ago
- 最基本最小白的自然语言处理入门读物，基于deepseek-r1，涵盖了传统NLP和现代大模型☆23Jan 16, 2026Updated 2 months ago
- 快播播放器的小DEMO，可以播放本地视频，也可以播放远程服务器的视频。☆10Jun 2, 2021Updated 4 years ago
- A modern Python library to work with Anoto dot patterns.☆16Aug 24, 2023Updated 2 years ago
- 收集的Unity3D插件以及资源、粒子等，欢迎Star☆13Jan 13, 2021Updated 5 years ago
- 视频监控系统的服务器端☆13Mar 3, 2016Updated 10 years ago
- ☆45Oct 5, 2025Updated 5 months ago
- ☆33Jan 29, 2023Updated 3 years ago
- ☆21Mar 11, 2025Updated last year
- Base on React's UI lib☆14Jan 7, 2023Updated 3 years ago
- 一个工具集的App，包含多个常用模块☆12Aug 1, 2020Updated 5 years ago
- 星搭低代码AI助手插件，使用 StableDiffusion 和 ChatGPT 生成插画和文案☆11Mar 22, 2023Updated 2 years ago
- This repository contains the source code related to the paper Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation☆11Jun 23, 2020Updated 5 years ago
- Implement Conditional VAE and train on MNIST by tensorflow 1.3.0.☆10Nov 7, 2017Updated 8 years ago
- Official repository for the paper "EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstructio…☆32Jun 15, 2025Updated 9 months ago
- MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation☆14Sep 2, 2024Updated last year
- This project is a versatile and powerful search tool that leverages state-of-the-art natural language processing models to provide releva…☆12Apr 3, 2023Updated 2 years ago
- Build OpenCV☆21Feb 7, 2026Updated last month
- Make a new landmarks or a less points landmarks from dlib ibug_300W_large_face_landmark_dataset.☆10Nov 11, 2018Updated 7 years ago
- flyai的场景分类比赛☆15Apr 1, 2019Updated 6 years ago
- An MCP-enabled Qwen3 0.6B demo with adjustable thinking budget, all in your browser!☆29Jun 2, 2025Updated 9 months ago
- An obsidian plugin to generate timelines from tags, folders, files or metadata automatically. 根据标签，文件夹，文件或者属性自动生成时间轴的插件。☆26Nov 26, 2025Updated 3 months ago
- Unity官方TreeView案例☆18Nov 14, 2019Updated 6 years ago
- OpenVLA Lightweight Version(0.5B). It uses qwen2-0.5B and fine-tunes using mllm format, without occupying LLM's inherent tokens. It repre…☆16Jan 7, 2026Updated 2 months ago
- [ICASSP'2025] "M³Rec: Selective State Space Models with Mixture-of-Modality Experts for Multi-Modal Sequential Recommendation"☆11Jul 9, 2025Updated 8 months ago