11 مستودعات
Technical frameworks, structural designs, and performance metrics used to analyze and categorize model capabilities.
Explore 11 awesome GitHub repositories matching artificial intelligence & ml · Model Architecture and Evaluation. Refine with filters or upvote what's useful.
DeepSeek-V3 is a large language model that provides comprehensive resources for model utilization, including technical specifications, pre-trained weights, and evaluation benchmarks. The project details the core transformer architecture, including parameter counts and multi-token prediction modules, while supporting native 8-bit floating-point quantization. The repository offers extensive support for local and distributed inference through integration with multiple frameworks and engines. It includes documentation for deploying the model across various hardware configurations, such as GPUs an
Standardized performance benchmarks and technical specifications allow for rigorous analysis of capabilities against industry-recognized metrics.
This repository serves as a centralized collection of state-of-the-art deep learning architectures and reference implementations designed for research and application development. It provides a comprehensive toolkit for computer vision and natural language processing, offering pre-built models and training pipelines for tasks ranging from image classification and object detection to complex sequence modeling. The project distinguishes itself by providing a flexible execution harness that manages the entire training lifecycle, including data ingestion and backpropagation. It supports scalable
Houses a centralized library of state-of-the-art deep learning architectures and verified reference implementations.
ONNX is an open-source standard for machine learning interoperability that provides a unified format for representing neural network models. By defining a common set of operators and a standardized file structure, it enables models to be shared, exported, and executed consistently across different training frameworks and software ecosystems. The project functions as an intermediate representation layer that decouples model development from deployment. It utilizes a language-neutral binary serialization format to store model structures and weights, ensuring that computational graphs remain por
Maintains a centralized collection of pre-trained models for vision and language tasks to simplify integration.
OpenLLM is a framework for deploying, managing, and scaling open-source large language models
Connects external version control repositories containing model definitions to extend the local library with custom collections.
This project provides an animated Live2D character widget that can be embedded on any web page as an interactive mascot. The widget renders characters using the Cubism SDK on an HTML canvas, and can be deployed either via a content delivery network for zero-setup integration or self-hosted on a personal server for full control over asset delivery. The mascot responds to visitor actions through CSS selector-based interaction binding, displaying custom speech bubbles when users hover over or click specific page elements. Visitors can click and drag the character to reposition it anywhere on the
Points the widget to a static file server hosting Live2D model assets and JSON descriptions.
OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and
Structures deep learning models and generative AI assets into a directory format compatible with serving environments.
This repository provides a collection of reference implementations and code examples for training and deploying machine learning models using the MLX framework. It serves as a practical guide for executing distributed training, fine-tuning large language models, converting model weights, and implementing multimodal generative workflows. The project distinguishes itself through specialized examples for local hardware execution, featuring weight quantization to reduce memory usage and low-rank adaptation for parameter-efficient fine-tuning. It also includes scripts for transforming external mod
Provides a comprehensive collection of reference implementations for training and deploying models using the MLX framework.
MochiDiffusion is a local client for Stable Diffusion that functions as an AI image generation studio. It provides a workspace for performing text-to-image, image-to-image, and inpainting tasks, enabling the production of high-resolution images offline using local hardware and neural engine acceleration. The project includes a local model manager for importing, organizing, and converting machine learning models into compatible formats for offline execution. It features a ControlNet integration tool to guide structural composition and spatial layout, alongside a dedicated image upscaler that u
Organizes external model files within local filesystem paths to manage different generation styles.
StabilityMatrix is a centralized installer and orchestrator for Stable Diffusion web interfaces and their dependencies. It functions as a generative AI workspace and portable runtime, providing a unified interface to install and update AI image generation packages within isolated environments to prevent global system conflicts. The project distinguishes itself through a shared model manager that imports, organizes, and shares checkpoints across different installations. It utilizes a central model repository and filesystem mapping to allow multiple packages to access the same large binary asse
Implements a central model repository to share large binary checkpoints across different installed packages.
Pythia هو إطار عمل بحثي متعدد الوسائط ونظام تدريب موزع مصمم لبناء وتدريب وتقييم نماذج كبيرة تجمع بين البيانات البصرية واللغوية. يوفر بيئة معيارية لتطوير نماذج الرؤية واللغة، مع التركيز على دمج مدخلات الصور والنصوص في تمثيلات ميزات مشتركة. يستخدم إطار العمل بنية معيارية تفصل كتل بناء النموذج إلى مكونات قابلة للتبديل، مما يسمح بتكوين مرن لوحدات الرؤية واللغة. ويتضمن مجموعة معيارية لتنفيذ النماذج المرجعية مقابل مجموعات بيانات موحدة لإنشاء خطوط أساس أداء متسقة لمهام الرؤية واللغة. يدعم النظام خطوط أنابيب التدريب الموزعة لتوسيع نطاق تطوير النموذج عبر عقد حوسبة متعددة ويستخدم ملفات إعدادات خارجية لتعيين المعلمات الفائقة لضمان قابلية تكرار البحث.
Executes standardized versions of vision and language models to establish consistent performance baselines.
يوفر هذا المستودع مجموعة من نماذج التعلم العميق وهياكل الشبكات العصبية المصممة لمهام معالجة اللغات الطبيعية. يعمل كمكتبة لنماذج مدربة مسبقاً مصممة لمعالجة وتحليل وتوليد بيانات اللغة البشرية باستخدام إطار عمل TensorFlow. يستخدم المشروع نمذجة التسلسل إلى التسلسل وهياكل عصبية ذات طبقات للتعامل مع بيانات اللغة ذات الطول المتغير. من خلال استخدام الرسوم البيانية لتدفق البيانات الثابتة والتمثيلات القائمة على الموتر (tensor)، تنفذ النماذج عمليات رياضية لتحويل ميزات الإدخال إلى معانٍ لغوية مجردة. يمكن للمستخدمين تحميل تسلسلات الأوزان المدربة مسبقاً لتهيئة هذه الشبكات لمهام استنتاج محددة. تغطي المجموعة مجموعة واسعة من القدرات، بما في ذلك تصنيف النصوص، وترجمة اللغات، والتعرف على الكيانات المسماة. كما تدعم تحويل الكلام إلى نص، وتوليف النص إلى كلام، وتلخيص المستندات، وتوليد محتوى نصي حواري أو أصلي. بالإضافة إلى ذلك، يتضمن المستودع أدوات لتحليل الهياكل النحوية وتصور أوزان الانتباه لتفسير أنماط اتخاذ القرار في النموذج.
Acts as a repository of pre-trained deep learning architectures for linguistic applications.