Lists (4)
Stars
In this repo there are some tips and a template to train your YOLO model for any kind of computer vision application
MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 60.2% Avg@8 score on the challenging GAIA benchmark.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems", which is `dmls-book`
The fastai book, published as Jupyter Notebooks
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Neural Networks: Zero to Hero
SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.
Run Windows apps such as Microsoft Office/Adobe in Linux (Ubuntu/Fedora) and GNOME/KDE as if they were a part of the native OS, including Nautilus integration. Hard fork of https://github.com/Fmst…
Automatic CPU speed & power optimizer for Linux
Flexible toolkit for making desktop shells with QtQuick, for Wayland and X11
Automated Hyprland installer for Ubuntu. NOTE: Repo Branches as per Ubuntu Versions
Enable Opencode to authenticate against Antigravity (Google's IDE) via OAuth so you can use Antigravity rate limits and access models like gemini-3-pro and claude-opus-4-5-thinking with your Google…
Everforest colour palette for GTK
Websites, web apps, portfolios that look like desktop operating systems
✒ A free, self-hosted platform to sideload iOS apps without a computer
Cross-platform feature rich iOS/tvOS sideloading application. Supporting macOS, Linux, and Windows.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
SkyReels V1: The first and most advanced open-source human-centric video foundation model
Wan: Open and Advanced Large-Scale Video Generative Models
Unlock the secrets of your watch history, explore hidden connections between films, and delve into the depths of personalized recommendations. But tread carefully, for the Trakt API holds powers th…