> 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.nemotron_h_vl

## Module Contents

### Classes

| Name                                                                  | Description                                                |
| --------------------------------------------------------------------- | ---------------------------------------------------------- |
| [`LLM`](#nemo_curator-models-nemotron_h_vl-LLM)                       | -                                                          |
| [`NemotronHVL`](#nemo_curator-models-nemotron_h_vl-NemotronHVL)       | NemotronH hybrid Mamba-Attention VLM for video captioning. |
| [`SamplingParams`](#nemo_curator-models-nemotron_h_vl-SamplingParams) | -                                                          |

### Data

[`EXPECTED_VIDEO_TAG_PARTS`](#nemo_curator-models-nemotron_h_vl-EXPECTED_VIDEO_TAG_PARTS)

[`NemotronVariant`](#nemo_curator-models-nemotron_h_vl-NemotronVariant)

[`VIDEO_TAG_SPLIT_MAX`](#nemo_curator-models-nemotron_h_vl-VIDEO_TAG_SPLIT_MAX)

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

[`_NEMOTRON_REVISION_INFO`](#nemo_curator-models-nemotron_h_vl-_NEMOTRON_REVISION_INFO)

[`_NEMOTRON_VARIANTS_INFO`](#nemo_curator-models-nemotron_h_vl-_NEMOTRON_VARIANTS_INFO)

### API

```python
class nemo_curator.models.nemotron_h_vl.LLM()
```

```python
class nemo_curator.models.nemotron_h_vl.NemotronHVL(
    model_dir: str,
    model_variant: nemo_curator.models.nemotron_h_vl.NemotronVariant = 'nemotron',
    caption_batch_size: int = 8,
    max_output_tokens: int = 512,
    stage2_prompt_text: str | None = None,
    verbose: bool = False
)
```

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

NemotronH hybrid Mamba-Attention VLM for video captioning.

Supports multiple checkpoint variants from HuggingFace:

* nemotron / nemotron-bf16: BF16 precision (default)
* nemotron-fp8: FP8 quantized
* nemotron-nvfp4: NVFP4 quantized

Models are automatically downloaded from HuggingFace on first use.

Return HuggingFace model ID for the selected variant.

```python
nemo_curator.models.nemotron_h_vl.NemotronHVL._refine_caption_prompt(
    original_prompt: str,
    refinement_text: str
) -> str
```

Create a refined prompt for stage 2 captioning.

```python
nemo_curator.models.nemotron_h_vl.NemotronHVL.download_weights_on_node(
    model_dir: str,
    variant: nemo_curator.models.nemotron_h_vl.NemotronVariant = 'nemotron'
) -> None
```

classmethod

Download NemotronH VL weights from HuggingFace.

Models are automatically downloaded from HuggingFace Hub on first use.
Supports multiple quantization variants for different performance/memory tradeoffs.

**Parameters:**

Base directory for model weights. The model will be downloaded
to a subdirectory named after the HuggingFace model ID.

Model variant to download. Options:

* "nemotron" or "nemotron-bf16": BF16 precision (default)
* "nemotron-fp8": FP8 quantized
* "nemotron-nvfp4": NVFP4 quantized

```python
nemo_curator.models.nemotron_h_vl.NemotronHVL.generate(
    videos: list[dict[str, typing.Any]],
    generate_stage2_caption: bool = False,
    batch_size: int = 16
) -> list[str]
```

```python
nemo_curator.models.nemotron_h_vl.NemotronHVL.setup() -> None
```

```python
class nemo_curator.models.nemotron_h_vl.SamplingParams()
```

```python
nemo_curator.models.nemotron_h_vl.EXPECTED_VIDEO_TAG_PARTS = 2
```

```python
nemo_curator.models.nemotron_h_vl.NemotronVariant = Literal['nemotron', 'nemotron-bf16', 'nemotron-fp8', 'nemotron-nvfp4']
```

```python
nemo_curator.models.nemotron_h_vl.VIDEO_TAG_SPLIT_MAX = 1
```

```python
nemo_curator.models.nemotron_h_vl.VLLM_AVAILABLE = True
```

```python
nemo_curator.models.nemotron_h_vl._NEMOTRON_REVISION_INFO: Final = {'nemotron': '5d250e2e111dc5e1434131bdf3d590c27a878ade', 'nemotron-bf16': '5d250...
```

```python
nemo_curator.models.nemotron_h_vl._NEMOTRON_VARIANTS_INFO: Final = {'nemotron': 'nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16', 'nemotron-bf16': 'nvi...
```