mode — Model Optimizer 0.27.1 (original) (raw)
Sparsity mode descriptor.
Classes
| ExportSparseModeDescriptor | Class to describe the "export_sparse" mode. |
|---|---|
| SparseGPTModeDescriptor | Class to define and describe sparsification based on SparseGPT. |
| SparseMagnitudeModeDescriptor | Class to define and describe magnitude-based sparsification. |
Functions
| convert_sparse_model | Function for converting a model to a sparsity meta-model. |
|---|---|
| export_sparse | Export a sparse model to a regular model. |
| restore_export_sparse | Restore & export a sparse model to a regular model. |
| restore_sparse_model | Function for restoring a previously convert model to a sparsity meta-model. |
| update_sparse_metadata | Update subnet config to current subnet config of model. |
class ExportSparseModeDescriptor
Bases: _ModeDescriptor
Class to describe the "export_sparse" mode.
The properties of this mode can be inspected via the source code.
property config_class_: type[ModeloptBaseConfig]_
Specifies the config class for the mode.
property convert_: Callable[[Module, ModeloptBaseConfig], tuple[Module, dict[str, Any]]]_
The mode’s entrypoint for converting a model.
property is_export_mode_: bool_
Specifies if this mode is an export mode.
property name_: str_
Returns the value (str representation) of the mode.
property restore_: Callable[[Module, ModeloptBaseConfig, dict[str, Any]], Module]_
The mode’s entrypoint for restoring a model.
class SparseGPTModeDescriptor
Bases: SparseMagnitudeModeDescriptor
Class to define and describe sparsification based on SparseGPT.
property config_class_: type[ModeloptBaseConfig]_
Specifies the config class for the mode.
property name_: str_
Returns the name of the mode.
property search_algorithm_: type[BaseSearcher]_
Specifies the search algorithm for the mode.
class SparseMagnitudeModeDescriptor
Bases: _ModeDescriptor
Class to define and describe magnitude-based sparsification.
property config_class_: type[ModeloptBaseConfig]_
Specifies the config class for the mode.
property convert_: Callable[[Module, ModeloptBaseConfig], tuple[Module, dict[str, Any]]]_
The mode’s entrypoint for converting a model.
property export_mode_: str | None_
The mode that corresponds to the export mode of this mode.
property name_: str_
Returns the name of the mode.
property next_modes_: set[str] | None_
Specifies the next modes for the mode.
property restore_: Callable[[Module, ModeloptBaseConfig, dict[str, Any]], Module]_
The mode’s entrypoint for restoring a model.
property search_algorithm_: type[BaseSearcher]_
Specifies the search algorithm for the mode.
property update_for_new_mode_: Callable[[Module, ModeloptBaseConfig, dict[str, Any]], None]_
The mode’s entrypoint for updating the models metadata.
property update_for_save_: Callable[[Module, ModeloptBaseConfig, dict[str, Any]], None]_
The mode’s entrypoint for updating the models metadata.
convert_sparse_model(model, config)
Function for converting a model to a sparsity meta-model.
Parameters:
- model (Module) –
- config (ModeloptBaseConfig) –
Return type:
_tuple_[Module, _dict_[str, _Any_]]
export_sparse(model, config)
Export a sparse model to a regular model.
Parameters:
- model (Module) –
- config (ExportSparseConfig) –
Return type:
_tuple_[Module, _dict_[str, _Any_]]
restore_export_sparse(model, config, metadata)
Restore & export a sparse model to a regular model.
Parameters:
- model (Module) –
- config (ExportSparseConfig) –
- metadata (dict [ str , Any ]) –
Return type:
Module
restore_sparse_model(model, config, metadata)
Function for restoring a previously convert model to a sparsity meta-model.
Parameters:
- model (Module) –
- config (ModeloptBaseConfig) –
- metadata (dict [ str , Any ]) –
Return type:
Module
update_sparse_metadata(model, config, metadata)
Update subnet config to current subnet config of model.
Parameters:
- model (Module) –
- config (ModeloptBaseConfig) –
- metadata (dict [ str , Any ]) –
Return type:
None