Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

workspace是基于C++11的轻量级异步执行框架，支持：通用任务异步并发执行、优先级任务调度、自适应动态线程池、高效静态线程池、异常处理机制等。

Trying to make python selenium more stealthy.

V2rayU,基于v2ray核心的mac版客户端,用于科学上网,使用swift编写,支持trojan,vmess,shadowsocks,socks5等服务协议,支持订阅, 支持二维码,剪贴板导入,手动配置,二维码分享等

This repository is an official implementation of the paper "LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection".

A modular graph-based Retrieval-Augmented Generation (RAG) system

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

Brand new TTS solution

Models, data loaders and abstractions for language processing, powered by PyTorch

🤖 PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

pytorch复现transformer

[ICML 2024] EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

飞桨大模型开发套件，提供大语言模型、跨模态大模型、生物计算大模型等领域的全流程开发工具链。

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high …

a few operators of opencv implement by arm neon

很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。

renderscript的官方替代品。

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

Your image is almost there!

一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.

Flutter widgets and themes implementing the current macOS design language.

A generative speech model for daily dialogue.

YOLOv10: Real-Time End-to-End Object Detection

🌀 Browse the web from a web page. Remote browser isolation. For security, privacy and more! By https://github.com/dosyago

[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Examples in the MLX framework

Official electron build of draw.io

🚀 基于 LLM 大语言模型的知识库问答系统。开箱即用、模型中立、灵活编排，支持快速嵌入到第三方业务系统，1Panel 官方出品。