Fullmoon: iOS App for Native Large Language Modeling Chats
General Description Fullmoon is an application designed for iOS devices and aims to provide the ability to chat privately with native large language models. The app is optimized for Apple Silicon and is supported on iPhone, iPad and Mac. Users of the chat...
Qwen2.5-Max based on MoE architecture fully outperforms DeepSeek V3
模型概览 近年来，基于混合专家系统（Mixture of Experts，MoE）架构的大模型训练成为人工智能领域的重要研究方向。Qwen团队近期发布的Qwen2.5-Max模型，采用超过20万亿to...
Onlook: open source Cursor for front-end design, design and publish code in React applications
综合介绍 Onlook是一款开源的设计工具，专为设计师和开发者打造，允许用户直接在运行的React应用中进行设计，并将设计修改转换为代码。该工具提供了一种直观的视觉编辑体验，类似于Figma或Webf...
YuE: Transforms lyrics into a base model of a complete song, supporting a wide range of musical styles
General Introduction YuE is an open source full song generation base model that focuses on transforming lyrics into full songs. Unlike other models that can only generate short snippets of non-vocal music, YuE is capable of generating full songs with lead and backing vocals up to several minutes in length. The model addresses music generation in...
PocketPal AI: A Small Language Modeling Chat Tool for Offline Use on iOS and Android Devices
综合介绍 PocketPal AI 是一款开源的移动应用，旨在将小型语言模型（Small Language Models, SLMs）直接引入到你的手机中，无论是iOS还是Android用户都可以使用...
Cog-ComfyUI: Running ComfyUI Workflows with APIs
综合介绍 Cog-ComfyUI是一个开源项目，旨在通过API运行ComfyUI工作流。该项目由GitHub用户fofr创建，提供了一种高效的方式来集成和运行ComfyUI工作流。ComfyUI是一种...
Supermemory: Importing bookmarks and web content to build a personal knowledge base
综合介绍 Supermemory 是一个开源项目，旨在帮助用户构建自己的“第二大脑”。它通过一个功能强大的 Chrome 扩展程序和AI技术，让用户能够轻松保存、组织和检索来自网页、Twitter书签...
Open NotebookLM: convert PDF to podcasts of open source tools
General Introduction Open NotebookLM is an open source project designed to convert any PDF document into a podcast. The tool utilizes open source Large Language Model (LLM) and Text-to-Speech (TTS) models to process PDF content and generate natural dialog suitable for audio podcasts...
Deeptrain: converting video content into large model retrievable information
综合介绍 Deeptrain是一个专注于AI视频处理的平台，通过其先进的技术，支持超过200种语言模型，能够有效地将视频内容整合到各种AI应用中。用户可以直接通过提供视频URL进行模型训练，无需下载视...
Qwen2.5-VL: an open source multimodal grand model supporting image-video document parsing
综合介绍 Qwen2.5-VL 是阿里巴巴云（Alibaba Cloud）Qwen 团队开发的开源多模态大模型。它能同时处理文本、图像、视频和文档，是 Qwen2-VL 的升级版，基于 Qwen2.5...
English 
简体中文 
日本語 
한국어 
Español 
Deutsch 
Français 
Português do Brasil