> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/v0.5/nemo-automodel/nemo_automodel/components/models/deepseek_v32/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

## Submodules

* **[`nemo_automodel.components.models.deepseek_v32.config`](/nemo-automodel/nemo_automodel/components/models/deepseek_v32/config)**
* **[`nemo_automodel.components.models.deepseek_v32.layers`](/nemo-automodel/nemo_automodel/components/models/deepseek_v32/layers)**
* **[`nemo_automodel.components.models.deepseek_v32.model`](/nemo-automodel/nemo_automodel/components/models/deepseek_v32/model)**
* **[`nemo_automodel.components.models.deepseek_v32.state_dict_adapter`](/nemo-automodel/nemo_automodel/components/models/deepseek_v32/state_dict_adapter)**

## Docs

- [nemo_automodel.components.models.deepseek_v32.config](https://docs.nvidia.com/nemo/automodel/v0.5/nemo-automodel/nemo_automodel/components/models/deepseek_v32/config.md)
- [nemo_automodel.components.models.deepseek_v32.layers](https://docs.nvidia.com/nemo/automodel/v0.5/nemo-automodel/nemo_automodel/components/models/deepseek_v32/layers.md)
- [nemo_automodel.components.models.deepseek_v32.model](https://docs.nvidia.com/nemo/automodel/v0.5/nemo-automodel/nemo_automodel/components/models/deepseek_v32/model.md)
- [nemo_automodel.components.models.deepseek_v32.state_dict_adapter](https://docs.nvidia.com/nemo/automodel/v0.5/nemo-automodel/nemo_automodel/components/models/deepseek_v32/state_dict_adapter.md)