primeqa.calibration.train_confidence_calibrator.ModelArguments

class primeqa.calibration.train_confidence_calibrator.ModelArguments(model_name_or_path: str, config_name: Optional[str] = None, tokenizer_name: Optional[str] = None, cache_dir: Optional[str] = None)

Bases: object

Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.

Methods

Attributes

cache_dir
config_name
tokenizer_name
model_name_or_path