Github Top Repositories
Photo
๐ฏ lyogavin/airllm landed on trending. Worth a proper look.
๐ https://github.com/lyogavin/airllm
๐ AirLLM 70B inference with single 4GB GPU
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
AirLLM is a game-changer for large language models, allowing them to run on significantly less GPU memory without sacrificing performance. With AirLLM, you can run massive models like 405B Llama 3.1 on just 8GB of GPU memory or DeepSeek-V3 (671B) on around 12GB. The secret lies in its ability to stream one expert at a time, rather than loading the entire layer.
To get started, simply install the
AirLLM supports a wide range of models, including ChatGLM, QWen, Baichuan, and more. It's perfect for researchers, developers, and enthusiasts looking to push the boundaries of language modeling.
In short, AirLLM is a powerful tool that makes large language models more accessible and efficient. With its ease of use and impressive performance, it's a must-try for anyone working with language models: run bigger models, faster, and on less hardware.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
๐ https://github.com/lyogavin/airllm
๐ AirLLM 70B inference with single 4GB GPU
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
AirLLM is a game-changer for large language models, allowing them to run on significantly less GPU memory without sacrificing performance. With AirLLM, you can run massive models like 405B Llama 3.1 on just 8GB of GPU memory or DeepSeek-V3 (671B) on around 12GB. The secret lies in its ability to stream one expert at a time, rather than loading the entire layer.
To get started, simply install the
airllm package using pip install airllm and initialize the model with AutoModel.from_pretrained("model_id"). You can also enable model compression for up to 3x inference speedup by passing the compression argument.AirLLM supports a wide range of models, including ChatGLM, QWen, Baichuan, and more. It's perfect for researchers, developers, and enthusiasts looking to push the boundaries of language modeling.
In short, AirLLM is a powerful tool that makes large language models more accessible and efficient. With its ease of use and impressive performance, it's a must-try for anyone working with language models: run bigger models, faster, and on less hardware.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
โค1
Github Top Repositories
Photo
๐ Spotted on GitHub Trending: iv-org/invidious โ let's break it down.
๐ https://github.com/iv-org/invidious
๐ Invidious is an alternative front-end to YouTube
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The Invidious project is an open-source alternative front-end to YouTube, offering a lightweight and ad-free experience. Its key features include
From a technical standpoint, Invidious has
The target audience for Invidious includes anyone looking for a private and ad-free YouTube experience. Whether you're a casual user or a developer, Invidious provides a unique alternative to the traditional YouTube platform.
Invidious is all about taking back control of your YouTube experience - it's your videos, your way.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
๐ https://github.com/iv-org/invidious
๐ Invidious is an alternative front-end to YouTube
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The Invidious project is an open-source alternative front-end to YouTube, offering a lightweight and ad-free experience. Its key features include
no tracking, customizable homepage, and notifications for subscribed channels. Invidious can be used by selecting a public instance from the list or by hosting it yourself. From a technical standpoint, Invidious has
embedded video support and a developer API, and it does not use official YouTube APIs. The project is available in many languages and has a strong focus on community involvement, with opportunities to contribute code and translate the platform.The target audience for Invidious includes anyone looking for a private and ad-free YouTube experience. Whether you're a casual user or a developer, Invidious provides a unique alternative to the traditional YouTube platform.
Invidious is all about taking back control of your YouTube experience - it's your videos, your way.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
โค1
๐ฏ codecrafters-io/build-your-own-x landed on trending. Worth a proper look.
๐ https://github.com/codecrafters-io/build-your-own-x
๐ Master programming by recreating your favorite technologies from scratch.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The codecrafters-io/build-your-own-x GitHub repository is a treasure trove of guides for building various technologies from scratch. Its purpose is to help you learn by creating real-world projects, following the philosophy of Richard Feynman: "What I cannot create, I do not understand."
The repo offers a wide range of key features, including step-by-step tutorials, example code in multiple programming languages, and explanations of complex concepts. You can use these guides to build your own 3D renderer, AI model, augmented reality app, BitTorrent client, blockchain, bot, command-line tool, database, and many more.
Some technical highlights include the use of languages like C++, Java, Python, and JavaScript, as well as frameworks and libraries such as Unity and OpenCV. The guides also cover various topics, such as computer graphics, machine learning, networking, and cybersecurity.
This repository is suitable for developers of all levels, from beginners to experienced professionals, who want to improve their skills and learn by building real-world projects.
In short, building your own technology from scratch is the best way to learn, and this repository provides the perfect starting point - so, get building and create something amazing!
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
๐ https://github.com/codecrafters-io/build-your-own-x
๐ Master programming by recreating your favorite technologies from scratch.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The codecrafters-io/build-your-own-x GitHub repository is a treasure trove of guides for building various technologies from scratch. Its purpose is to help you learn by creating real-world projects, following the philosophy of Richard Feynman: "What I cannot create, I do not understand."
The repo offers a wide range of key features, including step-by-step tutorials, example code in multiple programming languages, and explanations of complex concepts. You can use these guides to build your own 3D renderer, AI model, augmented reality app, BitTorrent client, blockchain, bot, command-line tool, database, and many more.
Some technical highlights include the use of languages like C++, Java, Python, and JavaScript, as well as frameworks and libraries such as Unity and OpenCV. The guides also cover various topics, such as computer graphics, machine learning, networking, and cybersecurity.
This repository is suitable for developers of all levels, from beginners to experienced professionals, who want to improve their skills and learn by building real-world projects.
In short, building your own technology from scratch is the best way to learn, and this repository provides the perfect starting point - so, get building and create something amazing!
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
โค1
Github Top Repositories
Photo
๐ Meet zhaoxuya520/reverse-skill: a gem from today's GitHub trending list.
๐ https://github.com/zhaoxuya520/reverse-skill
๐ Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients ้ๅ/ๆธ้/ๅฎๅ จๆ่ฝ่ทฏ็ฑๅ - AI ่ชๅจ่ทฏ็ฑ + ๆ้่ชไธพๅทฅๅ ท้พ + ่ชๅจ่ฟๅ็ป้ชๅบ | ๆฏๆ Claude Code / Kiro / Cursor / Cline ็ญไปฃ็ AI ๅฎขๆท็ซฏ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The reverse-skill GitHub repository is a comprehensive cybersecurity skills router designed to navigate complex security tasks. It provides a structured approach to routing methodologies, checking available tools, and executing repeatable workflows for various scenarios, including APK analysis, binary reverse engineering, and penetration testing.
The repository includes key features such as a PRIMARY fast ladder, a task โ skill routing matrix, and a local tool status index. It supports multiple
To get
The target audience includes security professionals, researchers, and AI agents looking to streamline their workflow and improve efficiency. With its
In summary, reverse-skill is a powerful tool for cybersecurity professionals, providing a structured approach to complex security tasks - automate your workflow, amplify your skills.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
๐ https://github.com/zhaoxuya520/reverse-skill
๐ Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients ้ๅ/ๆธ้/ๅฎๅ จๆ่ฝ่ทฏ็ฑๅ - AI ่ชๅจ่ทฏ็ฑ + ๆ้่ชไธพๅทฅๅ ท้พ + ่ชๅจ่ฟๅ็ป้ชๅบ | ๆฏๆ Claude Code / Kiro / Cursor / Cline ็ญไปฃ็ AI ๅฎขๆท็ซฏ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The reverse-skill GitHub repository is a comprehensive cybersecurity skills router designed to navigate complex security tasks. It provides a structured approach to routing methodologies, checking available tools, and executing repeatable workflows for various scenarios, including APK analysis, binary reverse engineering, and penetration testing.
The repository includes key features such as a PRIMARY fast ladder, a task โ skill routing matrix, and a local tool status index. It supports multiple
platforms, including Windows, Linux, and macOS, and integrates various tools like IDA Pro, radare2, and Ghidra.To get
started, users need to clone the repository, refresh the tool index, and follow platform-specific documentation. The repository layout is well-organized, with separate sections for skills, scripts, and documentation.The target audience includes security professionals, researchers, and AI agents looking to streamline their workflow and improve efficiency. With its
MIT License and open-source dependencies, the project encourages contributions and collaboration.In summary, reverse-skill is a powerful tool for cybersecurity professionals, providing a structured approach to complex security tasks - automate your workflow, amplify your skills.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
Github Top Repositories
Photo
๐ Spotted on GitHub Trending: different-ai/openwork โ let's break it down.
๐ https://github.com/different-ai/openwork
๐ The open-source alternative to Claude Cowork (powered by opencode)
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The OpenWork project is a free, open-source desktop app designed for sharing AI workflows across various platforms, including macOS, Windows, and Linux. Its primary purpose is to provide a unified workspace where users can create, share, and reuse AI workflows, skills, and connected services with teammates or keep them private.
The key features include adding one OpenWork MCP to compatible agents like Codex, Claude Code, or Cursor, and reusing the same skills and connections across tools and machines. The desktop app offers a dedicated workspace, but it's not required, as users can access OpenWork from their existing AI agent. For larger organizations, the admin interface allows publishing capabilities, managing access, and configuring shared or per-user connections.
To get started, users can
The project is suitable for both individual users and larger organizations, providing a flexible and scalable solution for managing AI workflows. The OpenWork Den control plane enables teams to provision inference at scale, manage access, and publish skills and plugins.
In terms of technical highlights, OpenWork uses
The target audience includes AI enthusiasts, developers, and organizations looking to streamline their AI workflow management.
In short, OpenWork empowers users to create once, share anywhere, making AI workflow management more efficient and accessible. The ability to reuse and share workflows seamlessly across different platforms and tools is a game-changer, and that's what makes OpenWork a standout solution - workflows just got a whole lot more open.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
๐ https://github.com/different-ai/openwork
๐ The open-source alternative to Claude Cowork (powered by opencode)
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The OpenWork project is a free, open-source desktop app designed for sharing AI workflows across various platforms, including macOS, Windows, and Linux. Its primary purpose is to provide a unified workspace where users can create, share, and reuse AI workflows, skills, and connected services with teammates or keep them private.
The key features include adding one OpenWork MCP to compatible agents like Codex, Claude Code, or Cursor, and reusing the same skills and connections across tools and machines. The desktop app offers a dedicated workspace, but it's not required, as users can access OpenWork from their existing AI agent. For larger organizations, the admin interface allows publishing capabilities, managing access, and configuring shared or per-user connections.
To get started, users can
install OpenWork using a simple prompt in their AI agent or by downloading it from the official website. The OpenWork MCP brings assigned skills and plugins into any compatible agent, exposing tools like search_capabilities and execute_capability.The project is suitable for both individual users and larger organizations, providing a flexible and scalable solution for managing AI workflows. The OpenWork Den control plane enables teams to provision inference at scale, manage access, and publish skills and plugins.
In terms of technical highlights, OpenWork uses
Electron and Vite for development, and users can run multiple git worktrees at once using pnpm dev:worktree. The target audience includes AI enthusiasts, developers, and organizations looking to streamline their AI workflow management.
In short, OpenWork empowers users to create once, share anywhere, making AI workflow management more efficient and accessible. The ability to reuse and share workflows seamlessly across different platforms and tools is a game-changer, and that's what makes OpenWork a standout solution - workflows just got a whole lot more open.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
โค1
Forwarded from Machine Learning with Python
The first bot in the world of Telegram that offers free courses, free certificates. https://t.iss.one/UdemySybot
Telegram
Free Courses Bot
The first bot in the world of Telegram that offers free courses, free certificates.
Github Top Repositories
Photo
โก microsoft/generative-ai-for-beginners is making waves. Here's the full picture.
๐ https://github.com/microsoft/generative-ai-for-beginners
๐ 21 Lessons, Get Started Building with Generative AI
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The Microsoft Generative AI for Beginners GitHub repository offers a comprehensive 21-lesson course on building Generative AI applications. The course covers the fundamentals of Generative AI, including Large Language Models (LLMs), Prompt Engineering, and responsible AI development.
Key features of the course include:
-
- Support for
- A
To get started, you'll need basic knowledge of
Takeaway: With this course, you can learn the fundamentals of Generative AI and start building your own applications in no time.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
๐ https://github.com/microsoft/generative-ai-for-beginners
๐ 21 Lessons, Get Started Building with Generative AI
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
The Microsoft Generative AI for Beginners GitHub repository offers a comprehensive 21-lesson course on building Generative AI applications. The course covers the fundamentals of Generative AI, including Large Language Models (LLMs), Prompt Engineering, and responsible AI development.
Key features of the course include:
-
Python and TypeScript code samples - Support for
Azure OpenAI Service, Microsoft Foundry Models, OpenAI API, and Foundry Local- A
Course Setup lesson to help with development environment setupTo get started, you'll need basic knowledge of
Python or TypeScript and a GitHub account. The course is suitable for beginners and intermediate learners. Takeaway: With this course, you can learn the fundamentals of Generative AI and start building your own applications in no time.
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ง Channel: https://t.iss.one/GithubRe
โค1