utils_nlp/models/transformers/named_entity_recognition.py [40:77]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(self, model_name="bert-base-cased", to_lower=False, cache_dir="."):
        self.model_name = model_name
        self.to_lower = to_lower
        self.cache_dir = cache_dir
        self.tokenizer = AutoTokenizer.from_pretrained(
            model_name,
            do_lower_case=to_lower,
            cache_dir=cache_dir,
            output_loading_info=False,
        )

    @staticmethod
    def get_inputs(batch, device, model_name, train_mode=True):
        """
        Creates an input dictionary given a model name.

        Args:
            batch (tuple): A tuple containing input ids, attention mask,
                segment ids, and labels tensors.
            device (torch.device): A PyTorch device.
            model_name (bool): Model name used to format the inputs.
            train_mode (bool, optional): Training mode flag.
                Defaults to True.

        Returns:
            dict: Dictionary containing input ids, segment ids, masks, and labels.
                Labels are only returned when train_mode is True.
        """
        batch = tuple(t.to(device) for t in batch)
        if model_name in supported_models:
            if train_mode:
                inputs = {
                    "input_ids": batch[0],
                    "attention_mask": batch[1],
                    "labels": batch[3],
                }
            else:
                inputs = {"input_ids": batch[0], "attention_mask": batch[1]}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



utils_nlp/models/transformers/sequence_classification.py [38:75]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(self, model_name="bert-base-cased", to_lower=False, cache_dir="."):
        self.model_name = model_name
        self.to_lower = to_lower
        self.cache_dir = cache_dir
        self.tokenizer = AutoTokenizer.from_pretrained(
            model_name,
            do_lower_case=to_lower,
            cache_dir=cache_dir,
            output_loading_info=False,
        )

    @staticmethod
    def get_inputs(batch, device, model_name, train_mode=True):
        """
        Creates an input dictionary given a model name.

        Args:
            batch (tuple): A tuple containing input ids, attention mask,
                segment ids, and labels tensors.
            device (torch.device): A PyTorch device.
            model_name (bool): Model name used to format the inputs.
            train_mode (bool, optional): Training mode flag.
                Defaults to True.

        Returns:
            dict: Dictionary containing input ids, segment ids, masks, and labels.
                Labels are only returned when train_mode is True.
        """
        batch = tuple(t.to(device) for t in batch)
        if model_name in supported_models:
            if train_mode:
                inputs = {
                    "input_ids": batch[0],
                    "attention_mask": batch[1],
                    "labels": batch[3],
                }
            else:
                inputs = {"input_ids": batch[0], "attention_mask": batch[1]}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -