4 Repos
Execution patterns where model outputs are derived from state and inputs through stateless functions.
Distinct from Functional Transformations: Focuses on the application of pure functions to neural network forward passes for JIT and autograd compatibility.
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Pure Function Model Execution. Refine with filters or upvote what's useful.
Flax is a deep learning framework and JAX neural network library designed for building complex machine learning models. It functions as a distributed training library and model state manager, providing a toolkit for defining flexible neural network architectures and scaling their training across multiple hardware devices. The project is characterized by a design that separates network logic from parameter values to remain compatible with pure functions. It uses hierarchical module composition to organize networks as trees of nested modules and employs a reference-based state management system
Transforms model state and inputs into outputs through stateless functions to enable JAX transformations.
Trail of Bits identifies functions declared as constant/pure/view that change the state, potentially trapping contracts compiled with Solidity 0.5.
whisper-jax ist eine Hochleistungs-Implementierung des Whisper-Modells zur automatischen Spracherkennung, die unter Verwendung des JAX-Frameworks neu geschrieben wurde. Sie ist für beschleunigte Inferenz konzipiert und verwendet XLA-Kompilierung, um die Modellausführung auf Hardwarebeschleunigern zu optimieren. Das Projekt konzentriert sich auf TPU-optimierte Transkription, um einen hohen Durchsatz und hohe Geschwindigkeit zu erreichen. Es enthält eine Gewichtungs-Übersetzungspipeline, die vortrainierte Modellparameter von PyTorch in JAX-kompatible Arrays konvertiert. Das System unterstützt das Transkribieren von Audio in Text, das Übersetzen von Sprache in mehrere Sprachen und das Generieren von Audio-Zeitstempeln. Es ermöglicht die Stapelverarbeitung von Audio und skaliert die Leistung durch datenparalleles Batching und modellparallele Tensor-Partitionierung. Das Projekt bietet eine Methode, um das Transkriptionsmodell als Remote-Inferenz-Endpunkt mit einer Weboberfläche bereitzustellen.
Employs stateless functions for model execution to ensure compatibility with JIT compilation and automatic differentiation.
This project is a Python software development kit and framework for building applications that integrate with large language models. It serves as a multimodal content generator and vector embedding library, enabling the production and editing of text, images, audio, and video. The toolkit provides specialized capabilities for adapting base models through supervised and reinforcement training. It further distinguishes itself by offering tools for orchestrating complex workflows, including stateful chat sessions, the enforcement of structured output via schemas, and the integration of external
Connects a model to custom functions or external tools to request and receive real-world data.