> 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 AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/curator/_mcp/server.

# nemo_curator.stages.text.classifiers.utils

## Module Contents

### Classes

| Name                                                                                 | Description                                                        |
| ------------------------------------------------------------------------------------ | ------------------------------------------------------------------ |
| [`SortByLengthStage`](#nemo_curator-stages-text-classifiers-utils-SortByLengthStage) | Stage that sorts the input data by the length of the input tokens. |

### Data

[`DEBERTA_TOKENIZER_PADDING_SIDE`](#nemo_curator-stages-text-classifiers-utils-DEBERTA_TOKENIZER_PADDING_SIDE)

### API

```python
class nemo_curator.stages.text.classifiers.utils.SortByLengthStage()
```

**Bases:** [ProcessingStage\[DocumentBatch, DocumentBatch\]](/nemo-curator/nemo_curator/stages/base#nemo_curator-stages-base-ProcessingStage)

Stage that sorts the input data by the length of the input tokens.

**`name`** `= 'sort_by_length_stage'`

---

```python
nemo_curator.stages.text.classifiers.utils.SortByLengthStage.inputs() -> tuple[list[str], list[str]]
```

```python
nemo_curator.stages.text.classifiers.utils.SortByLengthStage.outputs() -> tuple[list[str], list[str]]
```

```python
nemo_curator.stages.text.classifiers.utils.SortByLengthStage.process(
    batch: nemo_curator.tasks.DocumentBatch
) -> nemo_curator.tasks.DocumentBatch
```

```python
nemo_curator.stages.text.classifiers.utils.DEBERTA_TOKENIZER_PADDING_SIDE = 'right'
```