Buckets:

|
download
raw
3.75 kB

AutoPeftModels

The AutoPeftModel classes loads the appropriate PEFT model for the task type by automatically inferring it from the configuration file. They are designed to quickly and easily load a PEFT model in a single line of code without having to worry about which exact model class you need or manually loading a PeftConfig.

AutoPeftModel[[peft.AutoPeftModel]]

peft.AutoPeftModel[[peft.AutoPeftModel]]

peft.AutoPeftModel(*args, **kwargs)

Source

from_pretrained[[peft.AutoPeftModel.from_pretrained]]

from_pretrained(pretrained_model_name_or_path, adapter_name: str = 'default', is_trainable: bool = False, config: Optional[PeftConfig] = None, revision: Optional[str] = None, import_allowlist: Optional[list[str]] = None, **kwargs)

Source

Parameters:

import_allowlist (list[str], optional, defaults to {get_default_import_allowlist()}) : AutoPeftModel will attempt to instantiate the base model that is configured in the adapter config. Since this operation needs to potentially import other packages, this allowlist is a safe-guard to prevent importing malicious packages. You may need to specify your package's import name here if it is not in the defaults.

A wrapper around all the preprocessing steps a user needs to perform in order to load a PEFT model. The kwargs are passed along to PeftConfig that automatically takes care of filtering the kwargs of the Hub methods and the config object init.

The parameters are equivalent to the ones of PeftModel.from_pretrained(). Differences are documented below.

AutoPeftModelForCausalLM[[peft.AutoPeftModelForCausalLM]]

peft.AutoPeftModelForCausalLM[[peft.AutoPeftModelForCausalLM]]

peft.AutoPeftModelForCausalLM(*args, **kwargs)

Source

AutoPeftModelForSeq2SeqLM[[peft.AutoPeftModelForSeq2SeqLM]]

peft.AutoPeftModelForSeq2SeqLM[[peft.AutoPeftModelForSeq2SeqLM]]

peft.AutoPeftModelForSeq2SeqLM(*args, **kwargs)

Source

AutoPeftModelForSequenceClassification[[peft.AutoPeftModelForSequenceClassification]]

peft.AutoPeftModelForSequenceClassification[[peft.AutoPeftModelForSequenceClassification]]

peft.AutoPeftModelForSequenceClassification(*args, **kwargs)

Source

AutoPeftModelForTokenClassification[[peft.AutoPeftModelForTokenClassification]]

peft.AutoPeftModelForTokenClassification[[peft.AutoPeftModelForTokenClassification]]

peft.AutoPeftModelForTokenClassification(*args, **kwargs)

Source

AutoPeftModelForQuestionAnswering[[peft.AutoPeftModelForQuestionAnswering]]

peft.AutoPeftModelForQuestionAnswering[[peft.AutoPeftModelForQuestionAnswering]]

peft.AutoPeftModelForQuestionAnswering(*args, **kwargs)

Source

AutoPeftModelForFeatureExtraction[[peft.AutoPeftModelForFeatureExtraction]]

peft.AutoPeftModelForFeatureExtraction[[peft.AutoPeftModelForFeatureExtraction]]

peft.AutoPeftModelForFeatureExtraction(*args, **kwargs)

Source

Xet Storage Details

Size:
3.75 kB
·
Xet hash:
995492120ff7116294bb9eba5a0c4adbea71a77c6016069486037c2f8a29992e

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.