>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")

>>> dataset = dataset.map(lambda examples: tokenizer(examples["text"]), batched=True)
>>> dataset[0]
{'text': 'the rock is destined to be the 21st century\'s new " conan " and that he\'s going to make a splash even greater than arnold schwarzenegger , jean-claud van damme or steven segal .', 
 'label': 1, 
 'input_ids': [101, 1996, 2600, 2003, 16036, 2000, 2022, 1996, 7398, 2301, 1005, 1055, 2047, 1000, 16608, 1000, 1998, 2008, 2002, 1005, 1055, 2183, 2000, 2191, 1037, 17624, 2130, 3618, 2084, 7779, 29058, 8625, 13327, 1010, 3744, 1011, 18856, 19513, 3158, 5477, 4168, 2030, 7112, 16562, 2140, 1012, 102], 
 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}

>>> dataset = dataset.map(lambda examples: tokenizer(examples["text"], return_tensors="np"), batched=True)

>>> label2id = {"entailment": 0, "neutral": 1, "contradiction": 2}

>>> label2id = {"contradiction": 0, "neutral": 1, "entailment": 2}

>>> from datasets import load_dataset

>>> mnli = load_dataset("nyu-mll/glue", "mnli", split="train")
>>> mnli_aligned = mnli.align_labels_with_mapping(label2id, "label")