Model Configuration

Configuring a model source can be done by specifying a mapping in the RIME JSON configuration file. Specify a Model discusses how to create a Python model file.

For an example of how to use this config in the model registry, please see the “Register a Model” step in Stress Tests walkthrough.

Template

{
    "hugging_face" :{
        "model_uri": "cross-encoder/nli-MiniLM2-L6-H768",
    }
}

Arguments

Parameter	Type	Description
model_path	String	Path to the Python model file.
hugging_face	String	The URI to a HuggingFace model.
kwargs	String	Arguments to pass to HuggingFace along with the URI.

Specify exactly one of model_path or hugging_face.