Awesome GitHub RepositoriesMachine Learning Model Formats

SurrealDB is a multi-model database engine designed to store and query document, graph, relational, and vector data within a single ACID-compliant platform. It functions as an AI-native data store, integrating vector search, graph traversal, and machine learning model execution directly into its query layer. By providing a unified declarative query language, the platform eliminates the need for external middleware to synchronize data across different storage models. The platform distinguishes itself through its ability to manage agent memory and complex workflows natively. It allows developer

Paddle is a deep learning framework designed for building, training, and deploying neural networks. It provides a platform for constructing models using tensor-based computations and supports both dynamic and static execution graphs to facilitate research and production workflows. The platform functions as a distributed machine learning system, enabling the scaling of training workloads across multiple nodes and hardware clusters. It includes a comprehensive toolkit for model deployment and optimization, allowing users to convert external model formats, compress trained models for resource-co

MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse

This is a cross-platform framework for building, training, and deploying custom machine learning models within the .NET ecosystem. It provides a predictive modeling engine for classification, regression, and forecasting tasks, alongside an inference runtime to generate predictions across different hardware architectures. The framework includes a gradient boosting library and supports interoperability with external models via a standardized open format. It features tools for prediction explainability, allowing the analysis of feature importance to debug model behavior and identify bias. The p

ipex-llm is an acceleration library and inference engine designed to optimize the execution and finetuning of large language models on Intel GPUs and NPUs. It provides a HuggingFace compatible model backend and a dedicated quantization toolkit for converting model weights into low-bit precision formats. The project facilitates distributed inference by splitting large model workloads across multiple accelerators using pipeline and tensor parallelism. It enables the deployment of models on Intel Arc, Flex, and Max GPUs to increase throughput and reduce latency. The library covers a broad range

Brain is a JavaScript library for building, training, and running feed-forward neural networks. It implements a multilayer perceptron model designed for pattern recognition and function approximation. The library includes a standalone inference engine that converts trained models into portable JavaScript functions. This allows predictions to be executed in browser or Node.js environments without requiring the original library dependencies. The system supports persistent model management through JSON serialization for saving and loading network weights. It also provides a streaming mechanism

The nexa-sdk is an on-device AI SDK and multimodal inference engine designed to run large language, vision, and audio models locally on mobile and desktop hardware. It functions as a local LLM runtime and NPU acceleration framework, enabling the execution of generative and discriminative models without reliance on cloud services. The project distinguishes itself through a dedicated NPU acceleration framework that optimizes model execution on Neural Processing Units to reduce latency and power consumption. It employs hardware-agnostic backend routing to dynamically distribute computations acro

This project is a containerized deployment for running Stable Diffusion web interfaces. It provides a portable runtime for generative AI that manages dependencies and hardware acceleration to enable text-to-image generation and image-to-image transformations via a browser-based interface. The system uses hardware-specific image tags to support both GPU-accelerated synthesis and CPU-only execution. It ensures environment isolation across different operating systems while utilizing bind-mount data persistence to keep heavy model weights and generated outputs on the host machine. The deployment

SerpentAI is a game AI development kit and computer vision framework designed for building autonomous agents that interact with video games. It serves as a game input automation tool and a machine learning model integration engine, allowing developers to create agents that perceive game states and execute actions. The framework utilizes a plugin-based agent architecture to provide modular extensions for game-specific logic and behaviors. It features a specialized system for training, bundling, and deploying machine learning classifiers to recognize visual contexts and game states in real time

Synonyms ist eine Natural-Language-Processing-Bibliothek und eine Engine für semantische Ähnlichkeit, die speziell für chinesische Texte entwickelt wurde. Sie fungiert als Word-Embedding-Toolkit und Tokenizer, der semantische Bedeutung extrahiert und Synonyme durch die Berechnung der konzeptionellen Nähe zwischen Wörtern und Sätzen identifiziert. Das System bietet ein Toolkit für chinesisches Word-Embedding und Synonym-Entdeckung, das den Abruf semantisch ähnlicher Wörter zur Erweiterung des Vokabulars ermöglicht. Es zeichnet sich durch einen konfigurationsgesteuerten Ansatz für das Laden von Modellen aus, der die Integration benutzerdefinierter Word-Embeddings unterstützt, um den semantischen Raum für Ähnlichkeitssuchen zu definieren. Die breiteren Funktionen umfassen chinesische Textsegmentierung mit Part-of-Speech-Tagging, Keyword-Extraktion und Textzusammenfassung. Die Bibliothek transformiert Rohtext in numerische Repräsentationen durch Wort- und Satzvektorisierung und verwendet Distanzmetriken, um semantische Ähnlichkeitsberechnungen und Vergleiche durchzuführen.

Keras-js ist eine JavaScript-Inferenz-Engine und ein browserbasiertes Machine-Learning-Framework, das darauf ausgelegt ist, vortrainierte Keras-neuronale Netze auszuführen. Es ermöglicht clientseitige Modell-Inferenz in Webbrowsern oder Node.js-Umgebungen, ohne dass ein Backend-Server erforderlich ist. Die Bibliothek nutzt einen WebGL-Tensor-Beschleuniger, um mathematische Operationen zur Hardwarebeschleunigung auf den Grafikprozessor abzubilden. Um die Reaktionsfähigkeit der Benutzeroberfläche während rechenintensiver Berechnungen aufrechtzuerhalten, integriert sie eine Web-Worker-Inferenz-Runtime, die die Verarbeitung neuronaler Netze in Hintergrund-Threads ausführt. Das System unterstützt das Laden von Modellen über JSON-Konfigurationsdateien und Gewichtungs-Tensoren. Es verwaltet große numerische Arrays unter Verwendung von WebGL-Texturspeicherung, um Hochgeschwindigkeits-Speicherzugriffe während der Tensor-Ausführung zu ermöglichen.

This repository is a collection of reference implementations, templates, and sample galleries for building and integrating machine learning models within the .NET ecosystem. It provides a set of practical demonstrations for implementing machine learning workflows using the ML.NET framework. The project emphasizes the integration of pre-trained models via the Open Neural Network Exchange format, allowing the execution of external machine learning logic within managed applications. It includes specific examples for loading and executing these standardized models to ensure cross-platform compati

Spark NLP is a toolkit for scalable text analysis and machine learning built on the Apache Spark distributed computing framework. It provides a multimodal machine learning framework and a distributed pipeline system for sequencing annotators to process large-scale linguistic data. The library includes a transformer text processor for generating contextual vector embeddings and a dedicated inference engine for managing large language models. The project distinguishes itself through its ability to process heterogeneous data types, including text, audio, and images, within a unified vision-langu

Safetensors is a secure tensor serialization format and library designed for storing and distributing model weights. Its primary purpose is to provide a safe file format for machine learning tensors that prevents the execution of arbitrary or malicious code during the deserialization process. The project is distinguished by its use of zero-copy memory mapping, which reads data from disk directly into memory to minimize overhead. It enables cross-framework compatibility, allowing tensor data to be serialized and deserialized across different machine learning libraries. The system covers high-