Wasp (Web Aapplications Specification) It is a full-stack web framework similar to Rails, using React, Node.js and Prisma, and the application can be deployed to any platform through the built-in CLI tool. advantage: Quick start:You can create and deploy production-ready web applications from scratch with just a few lines of clean, consistent declarative code. […]
F3D (pronounced as/fɛd/) is a fast and minimalistic 3D file viewer. It supports a wide variety of file formats, from digital content to scientific datasets (including glTF, STL, STEP, PLY, OBJ, FBX, Alembic), can display animations and supports thumbnails, and many rendering and texturing options, including physically based Real-time rendering and ray tracing. #F3D #Homepage
F3D Homepage, Documentation and Downloads – 3D File Viewer – News Fast Delivery Read More »
MOSS is an open source dialogue language model that supports Chinese-English bilingualism and various plug-ins.moss-moonThe series models have 16 billion parameters, and can run on a single A100/A800 or two 3090 graphics cards at FP16 precision, and can run on a single 3090 graphics card at INT4/8 precision. The MOSS pedestal language model is pre-trained
NetAxe is a network automation platform, aA fast-integrated front-end and back-end integration framework that makes NetDevOps simpler, faster, and more efficient.It uses technologies such as Django, Celery, Netmiko, and Nornir to build a back-end framework, and uses technologies such as Vue3, Typescript, and NaiveUI to build a modern front-end interface. It supports various types of
GPTCache is a library for creating semantic caches to store responses from LLM queries.Cut your LLM API cost by 10x and speed it up by 100x. ChatGPT and various large language models (LLMs) are incredibly versatile, enabling the development of a wide range of applications. However, as your application grows in popularity and encounters higher
MiniGPT-4 enhances visual-language understanding with advanced large-scale language models. MiniGPT-4 aligns the frozen vision encoder from BLIP-2 with the frozen LLM Vicuna using only one projection layer. The training of MiniGPT-4 is divided into two stages: The first traditional pre-training stage is trained using about 5 million aligned image-text pairs in 10 hours using
SdPaint is a simple Stable Diffusion painting python script, the user can draw on the canvas, and send each stroke of the image to the automatic1111 API, and update the canvas when the image is generated. Install Run the Start.bat file, it will create a venv and install some packages usage Make sure to run
Homarr is aA customizable browser homepage for interacting with your home server’s Docker containers (eg Sonarr/Radarr). Simplify server management with Homarr – a sleek, modern dashboard that puts all your apps and services at your fingertips. With Homarr, you can access and control everything in one convenient location. Homarr integrates seamlessly with the apps you
Ruff is a high-performance Python code analysis tool written based on Rust, which claims to be 10-100 times faster than existing similar tools. core features install via pip supportpyproject.toml Compatible with Python 3.11 More than 500 built-in rules, almost equivalent to Flake8’s built-in rule set Reimplemented dozens of Flake8 plugins,
EmuOS is an open source retro Windows system emulator, you only need a web browser to experience the retro Windows system and retro games/apps from the 90s, such as “Quake”, “Diablo”, ” Half-Life… to experience The main advantage of EmuOS is convenience, just open the EmuOS website(havemultiple mirrors), you can enter the system version selection
The StableLM project repository contains Stability AI’s ongoing development of the StableLM series of language models, and currently Stability AI has released the initial StableLM-alpha model set with 3 billion and 7 billion parameters. Models with 15 billion and 30 billion parameters are in development. Stability AI is currently at Hugging Face Spaces A demo
Semantic Kernel is a lightweight SDK that integrates AI Large Language Models (LLMs) with traditional programming languages. The Semantic Kernel extensible programming model combines natural language semantic capabilities, traditional code-native capabilities, and embedding-based memory to unlock new potential and add value to applications through AI. Semantic Kernel aims to support and encapsulate multiple design patterns
Milkman is an extensible request/response workbench, heavily inspired by Postman.The project authors say they are tired of those electron-based The application, because it takes a long time and a lot of memory to start; therefore a JavaFx based workbench was created to handle the request/response. It’s not limited to e.g. http (or more specifically REST)
Primus is a general-purpose distributed training scheduling framework for machine learning applications, which manages the training life cycle and data distribution of machine learning frameworks (such as Tensorflow, Pytorch), and helps the training framework to obtain better distributed capabilities. Function Multiple training framework support: Tensorflow, PyTorch, Monolith, etc.; Multi-scheduler support:
