Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型VisualGLM-6B 🤗 HF Repo • ⚒️ SwissArmyTransformer (sat) • 🐦 Twitter • 📃 [CogView@NeurIPS 21] [GitHub] • 📃 [GLM@ACL 22] [GitHub] 👋 加入我们的 Slack 和 WeChat 介绍 VisualGLM-6B 是一个开源的，支持图像、中文和英文的多模态对话语言模型，语言模型基于 ChatGLM-6B，具有 62 亿参数；图像部分通过训练 BLIP2-Qformer 构建起视觉模型与语言模型的桥梁，整体模型共78亿参数。 VisualGLM-6B 依靠来自于 CogView 数据集的30M高质量中文图文对，与300M经过筛选的英文图文对进行预训练，中英文权重相同。该训练方式较好地将视觉信息对齐到ChatGLM的语义空间；之后的微调阶段，模型在长视觉问答数据上训练，以生成符合人类偏好的答案…
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention [website] [demo] Abstract Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and hampers efficient deployment. Moreover, existing methods struggle with multi-subject generation as they often blend features among subjects. We present…
Drag & drop UI to build your customized LLM flow using LangchainJS Flowise - LangchainJS UI Drag & drop UI to build your customized LLM flow using LangchainJS ⚡Quick Start Install Flowise npm install -g flowise Start Flowise npx flowise start Open http://localhost:3000 🐳 Docker Go to docker folder at the root of the project Create .env file and specify the PORT (refer to .env.example) docker-compose up -d Open http://localhost:3000 You can bring the containers down by docker-comp…
A minimal operating system (2K LOC) on QEMU and a RISC-V boardVision This project's vision is to help every college student read all the code of an operating system. With only 2000 lines of code, egos-2000 implements every component of an operating system for education. It can run on a RISC-V board and also the QEMU software emulator. # The cloc utility is used to count the lines of code (LOC). # The command below counts the LOC of everything excluding text documents. > cloc egos-2000 -…
🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型LaWGPT：基于中文法律知识的大语言模型 LaWGPT 是一系列基于中文法律知识的开源大语言模型。 该系列模型在通用中文基座模型（如 Chinese-LLaMA、ChatGLM 等）的基础上扩充法律领域专有词表、大规模中文法律语料预训练，增强了大模型在法律领域的基础语义理解能力。在此基础上，构造法律领域对话问答数据集、中国司法考试数据集进行指令精调，提升了模型对法律内容的理解和执行能力。 详细内容请参考技术报告。 本项目持续开展，法律领域数据集及系列模型后续相继开源，敬请关注。 更新 🪴 2023/05/15：发布 中文法律数据源汇总（Awesome Chinese Legal Resources） 和 法律领域词表 🌟 2023/05/13：公开发布 Legal-Base-7B：法律基座模型，使用 50w 中文裁判文书数据二次预训…
MyWalletScan 关于 一款方便查看管理地址的工具 安装和使用 运行: git clone npm i npm run dev 说明 1. 本项目纯前端，不涉及任何后端，所有数据均通过浏览器访问zkSync和stark官方接口获取，不会上传任何数据。 2. 本项目数据全部存放于浏览器本地的localStorage中，不会上传任何数据。 3. 如果有bug或者建议，欢迎提issue或者pr。 4. 本项目仅供学习交流使用，不提供任何形式的技术支持，使用本项目产生的任何后果与本人无关。 5. 大家卷起来吧！ 使用 https://bitboxtools.github.io/
[updating ...] 自动量化交易机器人 Qbot is an AI-oriented quantitative investment platform, which aims to realize the potential, empower AI technologies in quantitative investment. https://ufund-me.github.io/Qbot :news: qbot-mini: https://github.com/Charmve/iQuant 🤖 Qbot Qbot website HOT Qbot platform TRY IT OUT AI驱动的自动化智能投研、智能投顾平台 Qbot is an AI-oriented automat…
Numbers every LLM developer should knowNumbers every LLM Developer should know At Google, there was a document put together by Jeff Dean, the legendary engineer, called Numbers every Engineer should know. It’s really useful to have a similar set of numbers for LLM developers to know that are useful for back-of-the envelope calculations. Here we share particular numbers we at Anyscale use, why the number is important and how to use it to your advantage. Notes on the Github version Last updates: …
StableStudio StableStudio by Stability AI 👋 Welcome to the community repository for StableStudio, the open-source version of DreamStudio 🗺 Contents – 🚀 Quick Start · ℹ️ About · 🙋 FAQ · 🧑💻 Contributing 📚 Documentation – 🎨 UI · 🔌 Plugins · ⚡️ platform.stability.ai 🔗 Links – 🎮 Discord · 🌈 DreamStudio · 🛟 Bugs & Support · 💬 Discussion 🚀 Quick Start You'll need to have Node.js and Yarn installed. Once that's done, you can run the following commands... git clone https://github.…