> 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.qwen_lm

## Module Contents

### Classes

| Name                                                            | Description          |
| --------------------------------------------------------------- | -------------------- |
| [`LLM`](#nemo_curator-models-qwen_lm-LLM)                       | -                    |
| [`QwenLM`](#nemo_curator-models-qwen_lm-QwenLM)                 | Qwen language model. |
| [`SamplingParams`](#nemo_curator-models-qwen_lm-SamplingParams) | -                    |

### Functions

| Name                                                                  | Description |
| --------------------------------------------------------------------- | ----------- |
| [`_weights_complete`](#nemo_curator-models-qwen_lm-_weights_complete) | -           |

### Data

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

[`_QWEN_LM_VARIANTS_INFO`](#nemo_curator-models-qwen_lm-_QWEN_LM_VARIANTS_INFO)

### API

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

<Indent />

<Anchor id="nemo_curator-models-qwen_lm-QwenLM">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    class nemo_curator.models.qwen_lm.QwenLM(
        model_dir: str = '',
        model_variant: str = 'qwen2.5',
        caption_batch_size: int = 1,
        fp8: bool = False,
        max_output_tokens: int = 512,
        vllm_kwargs = {}
    )
    ```
  </CodeBlock>
</Anchor>

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

  Qwen language model.

  <Anchor id="nemo_curator-models-qwen_lm-QwenLM-download_weights_on_node">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.qwen_lm.QwenLM.download_weights_on_node(
          model_dir: str,
          variant: str = 'qwen2.5'
      ) -> None
      ```
    </CodeBlock>
  </Anchor>

  <Indent>
    <Badge>
      classmethod
    </Badge>

    Download the weights for the QwenLM model on the node.
  </Indent>

  <Anchor id="nemo_curator-models-qwen_lm-QwenLM-generate">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.qwen_lm.QwenLM.generate(
          inputs: list[dict[str, typing.Any]]
      ) -> list[str]
      ```
    </CodeBlock>
  </Anchor>

  <Indent />

  <Anchor id="nemo_curator-models-qwen_lm-QwenLM-model_id_names">
    <CodeBlock showLineNumbers={false} wordWrap={true}>
      ```python
      nemo_curator.models.qwen_lm.QwenLM.model_id_names() -> list[str]
      ```
    </CodeBlock>
  </Anchor>

  <Indent />

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

  <Indent />
</Indent>

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

<Indent />

<Anchor id="nemo_curator-models-qwen_lm-_weights_complete">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    nemo_curator.models.qwen_lm._weights_complete(
        model_dir_path: pathlib.Path
    ) -> bool
    ```
  </CodeBlock>
</Anchor>

<Indent />

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

<Anchor id="nemo_curator-models-qwen_lm-_QWEN_LM_VARIANTS_INFO">
  <CodeBlock showLineNumbers={false} wordWrap={true}>
    ```python
    nemo_curator.models.qwen_lm._QWEN_LM_VARIANTS_INFO: Final = {'qwen2.5': ('Qwen/Qwen2.5-14B-Instruct', 'cf98f3b'), 'qwen3': ('Qwen/Qwen3-14B'...
    ```
  </CodeBlock>
</Anchor>