Stars
Master programming by recreating your favorite technologies from scratch.
micropuma / fastllm
Forked from ztxz16/fastllmfastllm是c++实现,后端无依赖(仅依赖CUDA,无需依赖PyTorch)的高性能大模型推理库。 可实现单4090推理DeepSeek R1 671B INT4模型,单路可达20+tps。
Pytorch implementation of a RGCN Link Prediction Model
🔥🔥🔥 专注于YOLO11,YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型,Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀
专注于改进RT-DETR模型,🚀 in PyTorch >, Support to improve backbone, neck, head, loss, IoU and other modules🚀based on Ultralytics
Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning
[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥
智元 IIM 是一款开源的网页版即时聊天系统, 同时拥有AI聊天对话功能, 支持ChatGPT、Midjourney、文心一言、讯飞星火、通义千问等AI助手功能
A LaTeX Template for BUPT Bachelor Thesis (updated in 2018) 北京邮电大学学士学位论文LaTeX模板
Pytorch-Named-Entity-Recognition-with-BERT
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
End-to-End Object Detection with Transformers
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
The official Python client for the Hugging Face Hub.
The dataset for drone based detection and tracking is released, including both image/video, and annotations.
Official Implementation of NeurIPS 2024 paper "G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering""
LLM API 管理 & 分发系统,支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型,统一 API 适配,可用于 key 管理与二次分发。单可执行文件,提供 Docker 镜像,一键部署,开箱即用。LLM API management & k…
A modular graph-based Retrieval-Augmented Generation (RAG) system
提供了一种gpt大模型平替解决方案实现利用非gpt大模型去使用Graphrag,支持多类型大模型如本地大模型(Ollama)、阿里云通义千问、百度文心千帆、智谱ChatGML、讯飞星火认知、Ollama、Moonshot AI、Google Gemini等。示例代码使用阿里的通义千问大模型,其他大模型使用方式相同。
语音方案:百度语音库 baidulib、讯飞语音AIUI库 chatsdk、讯飞语音msc库 iflylib;支持全双工语音识别,边听边识别,适合快速集成,体验效果