nemo_automodel.components.models.deepseek_v32.model#
DeepSeek V3.2 Model.
Contains DeepseekV32Block, DeepseekV32Model, and DeepseekV32ForCausalLM. These classes subclass from DeepSeek V3, with the main difference being the use of DeepseekV32MLA (with Indexer) instead of the standard MLA.
Module Contents#
Classes#
Transformer block for DeepSeek V3.2. |
|
DeepSeek V3.2 Model. |
|
DeepSeek V3.2 for Causal Language Modeling. |
Data#
API#
- class nemo_automodel.components.models.deepseek_v32.model.DeepseekV32Block(
- layer_idx: int,
- config: nemo_automodel.components.models.deepseek_v32.config.DeepseekV32Config,
- moe_config: nemo_automodel.components.moe.config.MoEConfig,
- backend: nemo_automodel.components.models.common.BackendConfig,
Bases:
nemo_automodel.components.models.deepseek_v3.model.BlockTransformer block for DeepSeek V3.2.
Subclasses V3 Block, using DeepseekV32MLA (with Indexer) instead of the standard MLA.
Initialization
- class nemo_automodel.components.models.deepseek_v32.model.DeepseekV32Model(
- config: nemo_automodel.components.models.deepseek_v32.config.DeepseekV32Config,
- backend: nemo_automodel.components.models.common.BackendConfig,
- *,
- moe_config: nemo_automodel.components.moe.config.MoEConfig | None = None,
Bases:
nemo_automodel.components.models.deepseek_v3.model.DeepseekV3ModelDeepSeek V3.2 Model.
Subclasses V3 Model, using DeepseekV32Block instead of Block.
Initialization
- class nemo_automodel.components.models.deepseek_v32.model.DeepseekV32ForCausalLM(
- config: nemo_automodel.components.models.deepseek_v32.config.DeepseekV32Config,
- moe_config: nemo_automodel.components.moe.config.MoEConfig | None = None,
- backend: nemo_automodel.components.models.common.BackendConfig | None = None,
- **kwargs,
Bases:
nemo_automodel.components.models.deepseek_v3.model.DeepseekV3ForCausalLMDeepSeek V3.2 for Causal Language Modeling.
Subclasses V3 ForCausalLM, using DeepseekV32Model and DeepSeekV32StateDictAdapter.
Initialization
- classmethod from_config(
- config: nemo_automodel.components.models.deepseek_v32.config.DeepseekV32Config,
- moe_config: nemo_automodel.components.moe.config.MoEConfig | None = None,
- backend: nemo_automodel.components.models.common.BackendConfig | None = None,
- **kwargs,
- classmethod from_pretrained(
- pretrained_model_name_or_path: str,
- *model_args,
- **kwargs,
- nemo_automodel.components.models.deepseek_v32.model.ModelClass#
None