> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/curator/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/curator/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/curator/_mcp/server.

# 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

```python
class nemo_curator.models.base.ModelInterface()
```

Abstract

**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.

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).

```python
nemo_curator.models.base.ModelInterface.setup() -> None
```

abstract

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