How to use the simpletransformers.custom_models.models.BertForMultiLabelSequenceClassification function in simpletransformers

def __init__(self, model_type, model_name, num_labels=None, pos_weight=None, args=None, use_cuda=True):
        """
        Initializes a MultiLabelClassification model.

        Args:
            model_type: The type of model (bert, roberta)
            model_name: Default Transformer model name or path to a directory containing Transformer model file (pytorch_nodel.bin).
            num_labels (optional): The number of labels or classes in the dataset.
            pos_weight (optional): A list of length num_labels containing the weights to assign to each label for loss calculation.
            args (optional): Default args will be used if this parameter is not provided. If provided, it should be a dict containing the args that should be changed in the default args.
            use_cuda (optional): Use GPU if available. Setting to False will force model to use CPU only.
        """
        MODEL_CLASSES = {
            'bert':       (BertConfig, BertForMultiLabelSequenceClassification, BertTokenizer),
            'roberta':    (RobertaConfig, RobertaForMultiLabelSequenceClassification, RobertaTokenizer),
            'xlnet':      (XLNetConfig, XLNetForMultiLabelSequenceClassification, XLNetTokenizer),
            'xlm':        (XLMConfig, XLMForMultiLabelSequenceClassification, XLMTokenizer),
            'distilbert': (DistilBertConfig, DistilBertForMultiLabelSequenceClassification, DistilBertTokenizer),
            'albert':     (AlbertConfig, AlbertForMultiLabelSequenceClassification, AlbertTokenizer)
        }

        config_class, model_class, tokenizer_class = MODEL_CLASSES[model_type]
        if num_labels:
            self.config = config_class.from_pretrained(model_name, num_labels=num_labels)
            self.num_labels = num_labels
        else:
            self.config = config_class.from_pretrained(model_name)
            self.num_labels = self.config.num_labels
        self.tokenizer = tokenizer_class.from_pretrained(model_name)
        self.tokenizer = tokenizer_class.from_pretrained(model_name)

def __init__(self, config):
        super(BertForMultiLabelSequenceClassification, self).__init__(config)
        self.num_labels = config.num_labels
        self.bert = BertModel(config)
        self.dropout = nn.Dropout(config.hidden_dropout_prob)
        self.classifier = nn.Linear(config.hidden_size, self.config.num_labels)

        self.init_weights()

def __init__(self, model_type, model_name, num_labels=2, args=None, use_cuda=True):
        """
        Initializes a MultiLabelClassification model.

        Args:
            model_type: The type of model (bert, roberta)
            model_name: Default Transformer model name or path to a directory containing Transformer model file (pytorch_nodel.bin).
            num_labels (optional): The number of labels or classes in the dataset.
            args (optional): Default args will be used if this parameter is not provided. If provided, it should be a dict containing the args that should be changed in the default args.
            use_cuda (optional): Use GPU if available. Setting to False will force model to use CPU only.
        """
        MODEL_CLASSES = {
            'bert': (BertConfig, BertForMultiLabelSequenceClassification, BertTokenizer),
            'roberta': (RobertaConfig, RobertaForMultiLabelSequenceClassification, RobertaTokenizer),
            'xlnet': (XLNetConfig, XLNetForMultiLabelSequenceClassification, XLNetTokenizer),
            'xlm': (XLMConfig, XLMForMultiLabelSequenceClassification, XLMTokenizer),
            'distilbert': (DistilBertConfig, DistilBertForMultiLabelSequenceClassification, DistilBertTokenizer),
        }

        config_class, model_class, tokenizer_class = MODEL_CLASSES[model_type]
        self.tokenizer = tokenizer_class.from_pretrained(model_name)
        self.model = model_class.from_pretrained(model_name, num_labels=num_labels)
        self.num_labels = num_labels

        if use_cuda:
            if torch.cuda.is_available():
                self.device = torch.device("cuda")
            else:
                raise ValueError("'use_cuda' set to True when cuda is unavailable. Make sure CUDA is available or set use_cuda=False.")