***

layout: overview
slug: nemo-curator/nemo\_curator/models/base
title: nemo\_curator.models.base
--------------------------------

## Module Contents

### Classes

| Name                                                         | Description                                                                |
| ------------------------------------------------------------ | -------------------------------------------------------------------------- |
| [`ModelInterface`](#nemo_curator-models-base-ModelInterface) | Abstract base class that defines an interface for machine learning models. |

### API

<Anchor id="nemo_curator-models-base-ModelInterface">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    class nemo_curator.models.base.ModelInterface()
    ```
  </CodeBlock>
</Anchor>

<Indent>
  <Badge>
    Abstract
  </Badge>

  **Bases:** `ABC`

  Abstract base class that defines an interface for machine learning models.

  Specifically focused on their weight handling and environmental setup.

  This interface allows our pipeline code to download weights locally and setup models in a uniform
  way. It does not place any restrictions on how inference is run.

  <ParamField path="model_id_names" type="list[str]">
    Returns a list of model IDs associated with the model.

    In cosmos-curate, each model has an ID associated with it.
    This is often the huggingspace name for that model (e.g. Salesforce/instructblip-vicuna-13b).
  </ParamField>

  <Anchor id="nemo_curator-models-base-ModelInterface-setup">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.base.ModelInterface.setup() -> None
      ```
    </CodeBlock>
  </Anchor>

  <Indent>
    <Badge>
      abstract
    </Badge>

    Set up the model for use, such as loading weights and building computation graphs.
  </Indent>
</Indent>