This is the offiicial code for Faster Segment Anything (MobileSAM) project that makes SAM lightweight Faster Segment Anything (MobileSAM) 📌 MobileSAM paper is available at paper link. 📌 A demo of MobileSAM running on CPU is open at demo link. On our own Mac i5 CPU, it takes around 3s. On the hugging face demo, the interface and inferior CPUs make it slower but still works fine. 🍇 Media coverage and Projects that adapt from SAM to MobileSAM (Updates) 2023/06/29: AnyLabeling supports Mobile…
LightGlue: Local Feature Matching at Light Speed LightGlueLocal Feature Matching at Light Speed Philipp Lindenberger · Paul-Edouard Sarlin · Marc Pollefeys Paper LightGlue is a Graph Neural Network for local feature matching that introspects its confidences to 1) stop early if all predictions are ready and 2) remove points deemed unmatchable to save compute. This repository hosts the inference code for LightGlue, a lightweight feature match…
中国大模型中国大模型列表 旨在记录中国大模型发展情况，欢迎提供 线索 材料 PR Issue 本仓库同时持续深度分析开源开放的大模型以及数据集的情况。 大模型列表 序号 公司 大模型 省市 官网 说明 1 百度 文心一言 北京 ✔ 试用需账号 2 科大讯飞 星火 安徽合肥 ✔ 试用需账号 3 达观数据 曹植 上海 ✔ 试用需账号 4 阿里云 通义千问 浙江杭州 ✔ 试用需账号 5 复旦大学 MOSS 上海 ✔ 试用需账号 6 清华大学 ChatGLM 北京 ✔ 开源6B，智谱AI 7 华为 盘古 广东深圳 ✔ 华为+鹏城 8 智源人工智能研究院 悟道·天鹰 北京 ✔ 悟道3.0,视界视觉，AQUILA天鹰座，Aquila-7B,AquilaChat-7B,AquilaCode-7B-NV,AquilaCode-7B-TS 9 哈尔滨工业大学 本草 黑龙江哈尔滨 ✔ 医学；基于LLaMA；另有基于 ChatGLM 的Med-ChatGLM 10 贝壳 BELLE 北京 ✔ 基于BLOOMZ或LLaMA的多个模型 11 百川智能 …
经过精心筛选，从5000+个电报群组/频道/机器人中挑选出的优质推荐！如果您有更多值得推荐的电报群组/频道/机器人，欢迎在issue中留言或提交pull requests。感谢您的关注！【热门推荐】5000+优质Telegram群组、频道和机器人，精心筛选，助您迅速找到最佳选择 声明：本项目的所有内容均来源于网络，仅供学习和技术研究使用。 如果大家有发现存在敏感内容的群组、频道和机器人欢迎在issue中提交，会在第一时间处理。 GitHub项目直达 项目的背景故事 频道 Channel 公开的高质量 TG 频道推荐，可以根据自己喜好选择订阅 频道 订阅人数 简介 阿里云盘盘 115603 频道默认支持阿里云盘官方用户规范 A姐分享 102330 A姐分享订阅频道;分享资源、影视、软件和福利等有趣的东西 加密货币｜DeFi｜Web3 99230 最新的加密货币新闻，观点和数据分析，洞见市场发展 白丝即正义 85435 本频道会不定时推送一些绅士老爷们喜闻乐见的福利 科技新闻投稿 81692 频道日常推送科技新闻和互动消息 竹新社 78411 7…
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.ExLlama A standalone Python/C++/CUDA implementation of Llama for use with 4-bit GPTQ weights, designed to be fast and memory-efficient on modern GPUs. Disclaimer: The project is coming along, but it's still a work in progress! Hardware requirements I am developing on an RTX 4090 and an RTX 3090-Ti. Both cards support the CUDA kernels, but there might be incompatibilities with older …
Chat with Hacker News using natural language. Built with OpenAI Functions and Vercel AI SDK. ChatHN Chat with Hacker News using natural language. Built with OpenAI Functions and Vercel AI SDK. Introduction · Deploy Your Own · Setting Up Locally · Tech Stack · Contributing · License Introduction ChatHN is an open-source AI chatbot that uses OpenAI Functions and the Vercel AI SDK to interact with the Hacker News API with natural language. …
QGIS is a free, open source, cross platform (lin/win/mac) geographical information system (GIS) QGIS is a full-featured, user-friendly, free-and-open-source (FOSS) geographical information system (GIS) that runs on Unix platforms, Windows, and MacOS. Features 1. Flexible and powerful spatial data management 2. Beautiful cartography 3. Advanced and robust geospatial analysis 4. Powerful customization and extensibility 5. QGIS Server Under the hood Versions and release cycle Free and O…
OpenResume is a powerful open-source resume builder and resume parser. https://open-resume.com/OpenResume OpenResume is a powerful open-source resume builder and resume parser. The goal of OpenResume is to provide everyone with free access to a modern professional resume design and enable anyone to apply for jobs with confidence. Official site: https://open-resume.com ⚒️ Resume Builder OpenResume's resume builder allows user to create a modern professional resume easily. It has 5 Core Feat…
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型ChatGLM2-6B 🤗 HF Repo • 🐦 Twitter • 📃 [GLM@ACL 22] [GitHub] • 📃 [GLM-130B@ICLR 23] [GitHub] 👋 加入我们的 Slack 和 WeChat Read this in English 介绍 ChatGLM2-6B 是开源中英双语对话模型 ChatGLM-6B 的第二代版本，在保留了初代模型对话流畅、部署门槛较低等众多优秀特性的基础之上，ChatGLM2-6B 引入了如下新特性： 更强大的性能：基于 ChatGLM 初代模型的开发经验，我们全面升级了 ChatGLM2-6B 的基座模型。ChatGLM2-6B 使用了 GLM 的混合目标函数，经过了 1.4T 中英标识符的预训练与人类偏好对齐训练，评测结果显示，相比于初代模型，ChatGLM2-6B 在 MMLU（+23%）、CEval（+33%）、GSM8K（+571%） 、BBH（+60%）等数据集上的性能取得了大幅度的提升…