A Model within the Giza Platform is a sophisticated entity designed to serve trained machine learning (ML) models as an integral part of an action. It represents a core component in the Giza ecosystem, particularly for users who want to integrate verifiable ML capabilities into their workflows. The primary function of a Model is to facilitate the deployment and execution of verifiable ML models, making them an accessible and efficient tool for a wide range of applications.

Overview of Model

The versatility of a Model is one of its key attributes. It is engineered to support two distinct types of inferences: verifiable inferences and standard Python ML inferences. This dual capability ensures that a Model can adapt to various requirements and scenarios, providing users with the flexibility to switch between inference types as needed. The process of shifting from one inference type to another is streamlined, requiring no additional coding or alterations to the existing setup. This ease of transition highlights the Model's user-friendly and adaptable nature.

Furthermore, the integration of a Model within an action underscores its importance in the Giza Platform's workflow. By situating the Model within an action, it ensures that the verifiable ML capabilities are not standalone features but are embedded within the broader workflow processes. This integration allows for a more cohesive and unified approach to workflow management, where ML models become a seamless part of the overall workflow, contributing to the efficiency and effectiveness of the Giza Platform's capabilities.

Last updated