> 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.

# nemo_curator.models.nemotron_3_nano_omni

## Module Contents

### Classes

| Name                                                                               | Description                                               |
| ---------------------------------------------------------------------------------- | --------------------------------------------------------- |
| [`LLM`](#nemo_curator-models-nemotron_3_nano_omni-LLM)                             | -                                                         |
| [`Nemotron3NanoOmni`](#nemo_curator-models-nemotron_3_nano_omni-Nemotron3NanoOmni) | Nemotron 3 Nano Omni multimodal VLM for video captioning. |
| [`SamplingParams`](#nemo_curator-models-nemotron_3_nano_omni-SamplingParams)       | -                                                         |

### Data

[`VLLM_AVAILABLE`](#nemo_curator-models-nemotron_3_nano_omni-VLLM_AVAILABLE)

[`_EXPECTED_VIDEO_TAG_PARTS`](#nemo_curator-models-nemotron_3_nano_omni-_EXPECTED_VIDEO_TAG_PARTS)

[`_HF_MODEL_ID`](#nemo_curator-models-nemotron_3_nano_omni-_HF_MODEL_ID)

[`_HF_REVISION`](#nemo_curator-models-nemotron_3_nano_omni-_HF_REVISION)

[`_VIDEO_TAG_SPLIT_MAX`](#nemo_curator-models-nemotron_3_nano_omni-_VIDEO_TAG_SPLIT_MAX)

### API

<Anchor id="nemo_curator-models-nemotron_3_nano_omni-LLM">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    class nemo_curator.models.nemotron_3_nano_omni.LLM()
    ```
  </CodeBlock>
</Anchor>

<Indent />

<Anchor id="nemo_curator-models-nemotron_3_nano_omni-Nemotron3NanoOmni">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    class nemo_curator.models.nemotron_3_nano_omni.Nemotron3NanoOmni(
        model_dir: str,
        caption_batch_size: int = 8,
        max_output_tokens: int = 512,
        stage2_prompt_text: str | None = None,
        verbose: bool = False
    )
    ```
  </CodeBlock>
</Anchor>

<Indent>
  **Bases:** [ModelInterface](/nemo-curator/nemo_curator/models/base#nemo_curator-models-base-ModelInterface)

  Nemotron 3 Nano Omni multimodal VLM for video captioning.

  Weights are downloaded automatically from HuggingFace on first use.
  model\_dir is the base directory; weights are stored at model\_dir/\<\_HF\_MODEL\_ID>/.

  <ParamField path="model_id_names" type="list[str]" />

  <ParamField path="stage2_prompt" />

  <ParamField path="weight_file" type="= str(Path(model_dir) / _HF_MODEL_ID)" />

  <Anchor id="nemo_curator-models-nemotron_3_nano_omni-Nemotron3NanoOmni-_patch_config">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.nemotron_3_nano_omni.Nemotron3NanoOmni._patch_config(
          model_dir_path: pathlib.Path
      ) -> None
      ```
    </CodeBlock>
  </Anchor>

  <Indent>
    <Badge>
      staticmethod
    </Badge>
  </Indent>

  <Anchor id="nemo_curator-models-nemotron_3_nano_omni-Nemotron3NanoOmni-_refine_caption_prompt">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.nemotron_3_nano_omni.Nemotron3NanoOmni._refine_caption_prompt(
          original_prompt: str,
          refinement_text: str
      ) -> str
      ```
    </CodeBlock>
  </Anchor>

  <Indent />

  <Anchor id="nemo_curator-models-nemotron_3_nano_omni-Nemotron3NanoOmni-download_weights_on_node">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.nemotron_3_nano_omni.Nemotron3NanoOmni.download_weights_on_node(
          model_dir: str
      ) -> None
      ```
    </CodeBlock>
  </Anchor>

  <Indent>
    <Badge>
      classmethod
    </Badge>

    Download Nemotron3NanoOmni weights.
  </Indent>

  <Anchor id="nemo_curator-models-nemotron_3_nano_omni-Nemotron3NanoOmni-generate">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.nemotron_3_nano_omni.Nemotron3NanoOmni.generate(
          videos: list[dict[str, typing.Any]],
          generate_stage2_caption: bool = False,
          batch_size: int | None = None
      ) -> list[str]
      ```
    </CodeBlock>
  </Anchor>

  <Indent />

  <Anchor id="nemo_curator-models-nemotron_3_nano_omni-Nemotron3NanoOmni-setup">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.nemotron_3_nano_omni.Nemotron3NanoOmni.setup() -> None
      ```
    </CodeBlock>
  </Anchor>

  <Indent />
</Indent>

<Anchor id="nemo_curator-models-nemotron_3_nano_omni-SamplingParams">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    class nemo_curator.models.nemotron_3_nano_omni.SamplingParams()
    ```
  </CodeBlock>
</Anchor>

<Indent />

<Anchor id="nemo_curator-models-nemotron_3_nano_omni-VLLM_AVAILABLE">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    nemo_curator.models.nemotron_3_nano_omni.VLLM_AVAILABLE = True
    ```
  </CodeBlock>
</Anchor>

<Anchor id="nemo_curator-models-nemotron_3_nano_omni-_EXPECTED_VIDEO_TAG_PARTS">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    nemo_curator.models.nemotron_3_nano_omni._EXPECTED_VIDEO_TAG_PARTS = 2
    ```
  </CodeBlock>
</Anchor>

<Anchor id="nemo_curator-models-nemotron_3_nano_omni-_HF_MODEL_ID">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    nemo_curator.models.nemotron_3_nano_omni._HF_MODEL_ID: Final[str] = 'nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning'
    ```
  </CodeBlock>
</Anchor>

<Anchor id="nemo_curator-models-nemotron_3_nano_omni-_HF_REVISION">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    nemo_curator.models.nemotron_3_nano_omni._HF_REVISION: Final[str] = '23d21acd455d9836d50c48570a329bde77e08ba4'
    ```
  </CodeBlock>
</Anchor>

<Anchor id="nemo_curator-models-nemotron_3_nano_omni-_VIDEO_TAG_SPLIT_MAX">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    nemo_curator.models.nemotron_3_nano_omni._VIDEO_TAG_SPLIT_MAX = 1
    ```
  </CodeBlock>
</Anchor>