> 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.mimo_v2_flash.state_dict_adapter

## Module Contents

### Classes

| Name                                                                                                                            | Description                                                             |
| ------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
| [`MiMoV2FlashStateDictAdapter`](#nemo_automodel-components-models-mimo_v2_flash-state_dict_adapter-MiMoV2FlashStateDictAdapter) | Convert MiMo-V2-Flash HF checkpoints to Automodel's grouped MoE layout. |

### Functions

| Name                                                                                                              | Description |
| ----------------------------------------------------------------------------------------------------------------- | ----------- |
| [`_should_quantize_key`](#nemo_automodel-components-models-mimo_v2_flash-state_dict_adapter-_should_quantize_key) | -           |

### Data

[`NON_QUANTIZED_KEY_PATTERNS`](#nemo_automodel-components-models-mimo_v2_flash-state_dict_adapter-NON_QUANTIZED_KEY_PATTERNS)

[`logger`](#nemo_automodel-components-models-mimo_v2_flash-state_dict_adapter-logger)

### API

```python
class nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter.MiMoV2FlashStateDictAdapter(
    config: typing.Any,
    moe_config: nemo_automodel.components.moe.config.MoEConfig,
    backend: nemo_automodel.components.models.common.BackendConfig,
    dtype: torch.dtype = torch.bfloat16
)
```

**Bases:** [MoESplitExpertsStateDictMixin](/nemo-automodel/nemo_automodel/components/moe/state_dict_mixin#nemo_automodel-components-moe-state_dict_mixin-MoESplitExpertsStateDictMixin), [StateDictAdapter](/nemo-automodel/nemo_automodel/components/checkpoint/state_dict_adapter#nemo_automodel-components-checkpoint-state_dict_adapter-StateDictAdapter)

Convert MiMo-V2-Flash HF checkpoints to Automodel's grouped MoE layout.

HF stores routed experts as split per-expert projections:
`mlp.experts.{E}.{gate,up,down}_proj.weight`.  Automodel groups those
into `gate_and_up_projs` and `down_projs` so EP can shard experts
without materializing every expert on every rank.

```python
nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter.MiMoV2FlashStateDictAdapter._create_scale_inv_for_hf_key(
    key: str,
    weight: torch.Tensor
) -> torch.Tensor
```

```python
nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter.MiMoV2FlashStateDictAdapter._dequantize(
    state_dict: dict[str, typing.Any]
) -> dict[str, typing.Any]
```

```python
nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter.MiMoV2FlashStateDictAdapter.convert_single_tensor_to_hf(
    fqn: str,
    tensor: typing.Any,
    kwargs = {}
) -> list[tuple[str, typing.Any]]
```

```python
nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter.MiMoV2FlashStateDictAdapter.from_hf(
    hf_state_dict: dict[str, typing.Any],
    device_mesh: torch.distributed.device_mesh.DeviceMesh | None = None,
    kwargs = {}
) -> dict[str, typing.Any]
```

```python
nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter.MiMoV2FlashStateDictAdapter.to_hf(
    state_dict: dict[str, typing.Any],
    exclude_key_regex: str | None = None,
    quantization: bool = False,
    kwargs = {}
) -> dict[str, typing.Any]
```

Convert Automodel state\_dict to the HF MiMo-V2-Flash layout.

Note: The `quantization` parameter is accepted for interface
compatibility but is **ignored**. MiMo-V2-Flash is distributed as an
FP8 HF checkpoint, so this adapter always emits FP8 weights plus
`_scale_inv` companions for keys that match `_should_quantize_key`,
regardless of the caller's preference.

```python
nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter._should_quantize_key(
    key: str
) -> bool
```

```python
nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter.NON_QUANTIZED_KEY_PATTERNS = ['input_layernorm.weight', 'post_attention_layernorm.weight', 'norm.weight', 'lm...
```

```python
nemo_automodel.components.models.mimo_v2_flash.state_dict_adapter.logger = logging.getLogger(__name__)
```