Hugging Face's logo

PEFT documentation

Configuration

You are viewing v0.6.1 version. A newer version v0.13.0 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Configuration

The configuration classes stores the configuration of a PeftModel, PEFT adapter models, and the configurations of PrefixTuning, PromptTuning, and PromptEncoder. They contain methods for saving and loading model configurations from the Hub, specifying the PEFT method to use, type of task to perform, and model configurations like number of layers and number of attention heads.

PeftConfigMixin

class peft.config.PeftConfigMixin

< >

( peft_type: typing.Optional[peft.utils.peft_types.PeftType] = None auto_mapping: typing.Optional[dict] = None )

Parameters

  • peft_type (Union[~peft.utils.config.PeftType, str]) — The type of Peft method to use.

This is the base configuration class for PEFT adapter models. It contains all the methods that are common to all PEFT adapter models. This class inherits from PushToHubMixin which contains the methods to push your model to the Hub. The method save_pretrained will save the configuration of your adapter model in a directory. The method from_pretrained will load the configuration of your adapter model from a directory.

from_json_file

< >

( path_json_file: str **kwargs )

Parameters

  • path_json_file (str) — The path to the json file.

Loads a configuration file from a json file.

from_pretrained

< >

( pretrained_model_name_or_path: str subfolder: typing.Optional[str] = None **kwargs )

Parameters

  • pretrained_model_name_or_path (str) — The directory or the Hub repository id where the configuration is saved.
  • kwargs (additional keyword arguments, optional) — Additional keyword arguments passed along to the child class initialization.

This method loads the configuration of your adapter model from a directory.

save_pretrained

< >

( save_directory: str **kwargs )

Parameters

  • save_directory (str) — The directory where the configuration will be saved.
  • kwargs (additional keyword arguments, optional) — Additional keyword arguments passed along to the push_to_hub method.

This method saves the configuration of your adapter model in a directory.

PeftConfig

class peft.PeftConfig

< >

( peft_type: typing.Union[str, peft.utils.peft_types.PeftType] = None auto_mapping: typing.Optional[dict] = None base_model_name_or_path: str = None revision: str = None task_type: typing.Union[str, peft.utils.peft_types.TaskType] = None inference_mode: bool = False )

Parameters

  • peft_type (Union[~peft.utils.config.PeftType, str]) — The type of Peft method to use.
  • task_type (Union[~peft.utils.config.TaskType, str]) — The type of task to perform.
  • inference_mode (bool, defaults to False) — Whether to use the Peft model in inference mode.

This is the base configuration class to store the configuration of a PeftModel.

PromptLearningConfig

class peft.PromptLearningConfig

< >

( peft_type: typing.Union[str, peft.utils.peft_types.PeftType] = None auto_mapping: typing.Optional[dict] = None base_model_name_or_path: str = None revision: str = None task_type: typing.Union[str, peft.utils.peft_types.TaskType] = None inference_mode: bool = False num_virtual_tokens: int = None token_dim: int = None num_transformer_submodules: typing.Optional[int] = None num_attention_heads: typing.Optional[int] = None num_layers: typing.Optional[int] = None )

Parameters

  • num_virtual_tokens (int) — The number of virtual tokens to use.
  • token_dim (int) — The hidden embedding dimension of the base transformer model.
  • num_transformer_submodules (int) — The number of transformer submodules in the base transformer model.
  • num_attention_heads (int) — The number of attention heads in the base transformer model.
  • num_layers (int) — The number of layers in the base transformer model.

This is the base configuration class to store the configuration of PrefixTuning, PromptEncoder, or PromptTuning.

←PEFT model Tuners→