4 dépôts
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 est une implémentation haute performance du modèle de reconnaissance vocale automatique Whisper réécrite en utilisant le framework JAX. Il est conçu pour une inférence accélérée et utilise la compilation XLA pour optimiser l'exécution du modèle sur des accélérateurs matériels. Le projet se concentre sur la transcription optimisée pour TPU pour atteindre un débit et une vitesse élevés. Il inclut un pipeline de traduction de poids qui convertit les paramètres de modèles pré-entraînés de PyTorch en tableaux compatibles JAX. Le système prend en charge la transcription de l'audio en texte, la traduction de la parole dans plusieurs langues et la génération d'horodatages audio. Il permet le traitement audio par lots et met à l'échelle les performances grâce au traitement par lots parallèle aux données et au partitionnement de tenseurs parallèle au modèle. Le projet fournit une méthode pour déployer le modèle de transcription en tant qu'endpoint d'inférence distant avec une interface web.
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.