Model Archiver is a tool used for creating archives of trained neural net models that can be consumed by Multi-Model-Server inference.
copied from cf-staging / model-archiverUse the Model Archiver CLI to start create a .mar file.
A key feature of MMS is the ability to package all model artifacts into a single model archive file. It is a separate command line interface (CLI), model-archiver, that can take model checkpoints and package them into a .mar file. This file can then be redistributed and served by anyone using MMS. It takes in the following model artifacts: a model composed of one or more files, the description of the model's inputs in the form of a signature file, a service file describing how to handle inputs and outputs, and other optional assets that may be required to serve the model. The CLI creates a .mar file that MMS's server CLI uses to serve the models.