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`	State dict adapter for DeepSeek V3.2.

API

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

Bases: DeepSeekV3StateDictAdapter

State dict adapter for DeepSeek V3.2.

_base_non_quantized_keys

_indexer_non_quantized_keys

_non_quantized_keys

list[str]

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

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.

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.