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

# nemo_automodel.components.models.deepseek_v32.state_dict_adapter

State dict adapter for DeepSeek V3.2.

Extends DeepSeekV3StateDictAdapter with mappings for the new Indexer weights.

## Module Contents

### Classes

| Name                                                                                                                           | Description                           |
| ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------- |
| [`DeepSeekV32StateDictAdapter`](#nemo_automodel-components-models-deepseek_v32-state_dict_adapter-DeepSeekV32StateDictAdapter) | State dict adapter for DeepSeek V3.2. |

### API

```python
class nemo_automodel.components.models.deepseek_v32.state_dict_adapter.DeepSeekV32StateDictAdapter()
```

**Bases:** [DeepSeekV3StateDictAdapter](/nemo-automodel/nemo_automodel/components/models/deepseek_v3/state_dict_adapter#nemo_automodel-components-models-deepseek_v3-state_dict_adapter-DeepSeekV3StateDictAdapter)

State dict adapter for DeepSeek V3.2.

Get the full list of non-quantized keys including indexer keys.

```python
nemo_automodel.components.models.deepseek_v32.state_dict_adapter.DeepSeekV32StateDictAdapter._add_quantization_scale_inv_tensors(
    state_dict: dict[str, typing.Any]
) -> dict[str, typing.Any]
```

Add quantization scale tensors, handling indexer-specific keys.

```python
nemo_automodel.components.models.deepseek_v32.state_dict_adapter.DeepSeekV32StateDictAdapter.convert_single_tensor_to_hf(
    fqn: str,
    tensor: typing.Any,
    kwargs = {}
) -> list[tuple[str, typing.Any]]
```

Convert a single tensor from native format to HuggingFace format.

Handles both standard V3 tensors and V3.2 indexer tensors, ensuring
indexer LayerNorm weights are not quantized.