Optimum documentation

The Tasks Manager

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v1.13.2).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

The Tasks Manager

Exporting a model from one framework to some format (also called backend here) involves specifying inputs and outputs information that the export function needs. The way optimum.exporters is structured for each backend is as follows:

  • Configuration classes containing the information for each model to perform the export.
  • Exporting functions using the proper configuration for the model to export.

The role of the TasksManager is to be the main entry-point to load a model given a name and a task, and to get the proper configuration for a given (architecture, backend) couple. That way, there is a centralized place to register the task -> model class and (architecture, backend) -> configuration mappings. This allows the export functions to use this, and to rely on the various checks it provides.

Task names

The tasks supported might depend on the backend, but here are the mappings between a task name and the auto class for both PyTorch and TensorFlow.

It is possible to know which tasks are supported for a model for a given backend, by doing:

>>> from optimum.exporters.tasks import TasksManager

>>> model_type = "distilbert"
>>> # For instance, for the ONNX export.
>>> backend = "onnx"
>>> distilbert_tasks = list(TasksManager.get_supported_tasks_for_model_type(model_type, backend).keys())

>>> print(distilbert_tasks)
['default', 'fill-mask', 'text-classification', 'multiple-choice', 'token-classification', 'question-answering']

PyTorch

Task Auto Class
text-generation, text-generation-with-past AutoModelForCausalLM
feature-extraction, feature-extraction-with-past AutoModel
fill-mask AutoModelForMaskedLM
question-answering AutoModelForQuestionAnswering
text2text-generation, text2text-generation-with-past AutoModelForSeq2SeqLM
text-classification AutoModelForSequenceClassification
token-classification AutoModelForTokenClassification
multiple-choice AutoModelForMultipleChoice
image-classification AutoModelForImageClassification
object-detection AutoModelForObjectDetection
image-segmentation AutoModelForImageSegmentation
masked-im AutoModelForMaskedImageModeling
semantic-segmentation AutoModelForSemanticSegmentation
automatic-speech-recognition AutoModelForSpeechSeq2Seq

TensorFlow

Task Auto Class
text-generation, text-generation-with-past TFAutoModelForCausalLM
default, default-with-past TFAutoModel
fill-mask TFAutoModelForMaskedLM
question-answering TFAutoModelForQuestionAnswering
text2text-generation, text2text-generation-with-past TFAutoModelForSeq2SeqLM
text-classification TFAutoModelForSequenceClassification
token-classification TFAutoModelForTokenClassification
multiple-choice TFAutoModelForMultipleChoice
semantic-segmentation TFAutoModelForSemanticSegmentation

Reference

class optimum.exporters.TasksManager

< >

( )

Handles the task name -> model class and architecture -> configuration mappings.

create_register

< >

( backend: str overwrite_existing: bool = False ) → Callable[[str, Tuple[str, ...]], Callable[[Type], Type]]

Parameters

  • backend (str) — The name of the backend that the register function will handle.
  • overwrite_existing (bool, defaults to False) — Whether or not the register function is allowed to overwrite an already existing config.

Returns

Callable[[str, Tuple[str, ...]], Callable[[Type], Type]]

A decorator taking the model type and a the supported tasks.

Creates a register function for the specified backend.

Example:

>>> register_for_new_backend = create_register("new-backend")

>>> @register_for_new_backend("bert", "text-classification", "token-classification")
>>> class BertNewBackendConfig(NewBackendConfig):
>>>     pass

determine_framework

< >

( model_name_or_path: typing.Union[str, pathlib.Path] subfolder: str = '' framework: typing.Optional[str] = None cache_dir: str = '/root/.cache/huggingface/hub' ) → str

Parameters

  • model_name_or_path (Union[str, Path]) — Can be either the model id of a model repo on the Hugging Face Hub, or a path to a local directory containing a model.
  • subfolder (str, defaults to "") — In case the model files are located inside a subfolder of the model directory / repo on the Hugging Face Hub, you can specify the subfolder name here.
  • framework (Optional[str], optional) — The framework to use for the export. See above for priority if none provided.

Returns

str

The framework to use for the export.

Determines the framework to use for the export.

The priority is in the following order:

  1. User input via framework.
  2. If local checkpoint is provided, use the same framework as the checkpoint.
  3. If model repo, try to infer the framework from the cache if available, else from the Hub.
  4. If could not infer, use available framework in environment, with priority given to PyTorch.

get_all_tasks

< >

( ) → List

Returns

List

all the possible tasks.

Retrieves all the possible tasks.

get_exporter_config_constructor

< >

( exporter: str model: typing.Union[ForwardRef('PreTrainedModel'), ForwardRef('TFPreTrainedModel'), NoneType] = None task: str = 'feature-extraction' model_type: typing.Optional[str] = None model_name: typing.Optional[str] = None exporter_config_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None ) → ExportConfigConstructor

Parameters

  • exporter (str) — The exporter to use.
  • model (Optional[Union[PreTrainedModel, TFPreTrainedModel]], defaults to None) — The instance of the model.
  • task (str, defaults to "feature-extraction") — The task to retrieve the config for.
  • model_type (Optional[str], defaults to None) — The model type to retrieve the config for.
  • model_name (Optional[str], defaults to None) — The name attribute of the model object, only used for the exception message.
  • exporter_config_kwargs(`Optional[Dict[str, Any]], defaults to None`) — Arguments that will be passed to the exporter config class when building the config constructor.

Returns

ExportConfigConstructor

The ExportConfig constructor for the requested backend.

Gets the ExportConfigConstructor for a model (or alternatively for a model type) and task combination.

get_model_class_for_task

< >

( task: str framework: str = 'pt' model_type: typing.Optional[str] = None model_class_name: typing.Optional[str] = None library: str = 'transformers' )

Parameters

  • task (str) — The task required.
  • framework (str, defaults to "pt") — The framework to use for the export.
  • model_type (Optional[str], defaults to None) — The model type to retrieve the model class for. Some architectures need a custom class to be loaded, and can not be loaded from auto class.
  • model_class_name (Optional[str], defaults to None) — A model class name, allowing to override the default class that would be detected for the task. This parameter is useful for example for “automatic-speech-recognition”, that may map to AutoModelForSpeechSeq2Seq or to AutoModelForCTC.
  • library (str, defaults to transformers) — The library name of the model.

Attempts to retrieve an AutoModel class from a task name.

get_model_from_task

< >

( task: str model_name_or_path: typing.Union[str, pathlib.Path] subfolder: str = '' revision: typing.Optional[str] = None framework: typing.Optional[str] = None cache_dir: typing.Optional[str] = None torch_dtype: typing.Optional[ForwardRef('torch.dtype')] = None device: typing.Union[ForwardRef('torch.device'), str, NoneType] = None library_name: str = None **model_kwargs )

Parameters

  • task (str) — The task required.
  • model_name_or_path (Union[str, Path]) — Can be either the model id of a model repo on the Hugging Face Hub, or a path to a local directory containing a model.
  • subfolder (str, defaults to "") — In case the model files are located inside a subfolder of the model directory / repo on the Hugging Face Hub, you can specify the subfolder name here.
  • revision (Optional[str], optional) — Revision is the specific model version to use. It can be a branch name, a tag name, or a commit id.
  • framework (Optional[str], optional) — The framework to use for the export. See TasksManager.determine_framework for the priority should none be provided.
  • cache_dir (Optional[str], optional) — Path to a directory in which a downloaded pretrained model weights have been cached if the standard cache should not be used.
  • torch_dtype (Optional[torch.dtype], defaults to None) — Data type to load the model on. PyTorch-only argument.
  • device (Optional[torch.device], defaults to None) — Device to initialize the model on. PyTorch-only argument. For PyTorch, defaults to “cpu”.
  • model_kwargs (Dict[str, Any], optional) — Keyword arguments to pass to the model .from_pretrained() method.
  • library_name (Optional[str], optional) — The library name of the model. See TasksManager.infer_library_from_model for the priority should none be provided.

Retrieves a model from its name and the task to be enabled.

get_supported_model_type_for_task

< >

( task: str exporter: str )

Returns the list of supported architectures by the exporter for a given task.

get_supported_tasks_for_model_type

< >

( model_type: str exporter: str model_name: typing.Optional[str] = None ) → TaskNameToExportConfigDict

Parameters

  • model_type (str) — The model type to retrieve the supported tasks for.
  • exporter (str) — The name of the exporter.
  • model_name (Optional[str], defaults to None) — The name attribute of the model object, only used for the exception message.

Returns

TaskNameToExportConfigDict

The dictionary mapping each task to a corresponding ExportConfig constructor.

Retrieves the task -> exporter backend config constructors map from the model type.

infer_library_from_model

< >

( model_name_or_path: str subfolder: str = '' revision: typing.Optional[str] = None cache_dir: str = '/root/.cache/huggingface/hub' library_name: str = None ) → str

Parameters

  • model_name_or_path (str) — The model to infer the task from. This can either be the name of a repo on the HuggingFace Hub, an instance of a model, or a model class.
  • subfolder (str, defaults to "") — In case the model files are located inside a subfolder of the model directory / repo on the Hugging Face Hub, you can specify the subfolder name here.
  • revision (Optional[str], optional, defaults to None) — Revision is the specific model version to use. It can be a branch name, a tag name, or a commit id.
  • cache_dir (Optional[str], optional) — Path to a directory in which a downloaded pretrained model weights have been cached if the standard cache should not be used.
  • library_name (Optional[str], optional) — The library name of the model.

Returns

str

The library name automatically detected from the model repo.

Infers the library from the model repo.

infer_task_from_model

< >

( model: typing.Union[str, ForwardRef('PreTrainedModel'), ForwardRef('TFPreTrainedModel'), typing.Type] subfolder: str = '' revision: typing.Optional[str] = None ) → str

Parameters

  • model (str) — The model to infer the task from. This can either be the name of a repo on the HuggingFace Hub, an instance of a model, or a model class.
  • subfolder (str, optional, defaults to "") — In case the model files are located inside a subfolder of the model directory / repo on the Hugging Face Hub, you can specify the subfolder name here.
  • revision (Optional[str], defaults to None) — Revision is the specific model version to use. It can be a branch name, a tag name, or a commit id.

Returns

str

The task name automatically detected from the model repo.

Infers the task from the model repo.

standardize_model_attributes

< >

( model_name_or_path: typing.Union[str, pathlib.Path] model: typing.Union[ForwardRef('PreTrainedModel'), ForwardRef('TFPreTrainedModel')] subfolder: str = '' revision: typing.Optional[str] = None cache_dir: str = '/root/.cache/huggingface/hub' library_name: str = None )

Parameters

  • model_name_or_path (Union[str, Path]) — Can be either the model id of a model repo on the Hugging Face Hub, or a path to a local directory containing a model.
  • model (Union[PreTrainedModel, TFPreTrainedModel]) — The instance of the model.
  • subfolder (str, defaults to "") — In case the model files are located inside a subfolder of the model directory / repo on the Hugging Face Hub, you can specify the subfolder name here.
  • revision (Optional[str], optional, defaults to None) — Revision is the specific model version to use. It can be a branch name, a tag name, or a commit id.
  • cache_dir (Optional[str], optional) — Path to a directory in which a downloaded pretrained model weights have been cached if the standard cache should not be used.
  • library_name (Optional[str], optional) —: The library name of the model.

Updates the model for export. This function is suitable to make required changes to the models from different libraries to follow transformers style.