>>> from transformers import AutoTokenizer, DistilBertForMaskedLM
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google/distilbert-base-uncased")
>>> model = DistilBertForMaskedLM.from_pretrained("google/distilbert-base-uncased")

>>> inputs = tokenizer("The capital of France is <mask>.", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> # retrieve index of <mask>
>>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]

>>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
>>> tokenizer.decode(predicted_token_id)
...

>>> labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"]
>>> # mask labels of non-<mask> tokens
>>> labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100)

>>> outputs = model(**inputs, labels=labels)
>>> round(outputs.loss.item(), 2)
...

>>> import torch
>>> from transformers import AutoTokenizer, DistilBertForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("google/distilbert-base-uncased")
>>> model = DistilBertForSequenceClassification.from_pretrained("google/distilbert-base-uncased")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_id = logits.argmax().item()
>>> model.config.id2label[predicted_class_id]
...

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = DistilBertForSequenceClassification.from_pretrained("google/distilbert-base-uncased", num_labels=num_labels)

>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...

>>> import torch
>>> from transformers import AutoTokenizer, DistilBertForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("google/distilbert-base-uncased")
>>> model = DistilBertForSequenceClassification.from_pretrained("google/distilbert-base-uncased", problem_type="multi_label_classification")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = DistilBertForSequenceClassification.from_pretrained(
...     "google/distilbert-base-uncased", num_labels=num_labels, problem_type="multi_label_classification"
... )

>>> labels = torch.sum(
...     torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).loss

>>> from transformers import AutoTokenizer, DistilBertForMultipleChoice
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("distilbert-base-cased")
>>> model = DistilBertForMultipleChoice.from_pretrained("distilbert-base-cased")

>>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
>>> choice0 = "It is eaten with a fork and a knife."
>>> choice1 = "It is eaten while held in the hand."
>>> labels = torch.tensor(0).unsqueeze(0)  # choice0 is correct (according to Wikipedia ;)), batch size 1

>>> encoding = tokenizer([[prompt, choice0], [prompt, choice1]], return_tensors="pt", padding=True)
>>> outputs = model(**{k: v.unsqueeze(0) for k, v in encoding.items()}, labels=labels)  # batch size is 1

>>> # the linear classifier still needs to be trained
>>> loss = outputs.loss
>>> logits = outputs.logits

>>> from transformers import AutoTokenizer, DistilBertForTokenClassification
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google/distilbert-base-uncased")
>>> model = DistilBertForTokenClassification.from_pretrained("google/distilbert-base-uncased")

>>> inputs = tokenizer(
...     "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
... )

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_token_class_ids = logits.argmax(-1)

>>> # Note that tokens are classified rather then input words which means that
>>> # there might be more predicted token classes than words.
>>> # Multiple token classes might account for the same word
>>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
>>> predicted_tokens_classes
...

>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...

>>> from transformers import AutoTokenizer, DistilBertForQuestionAnswering
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google/distilbert-base-uncased")
>>> model = DistilBertForQuestionAnswering.from_pretrained("google/distilbert-base-uncased")

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()

>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
>>> tokenizer.decode(predict_answer_tokens, skip_special_tokens=True)
...

>>> # target is "nice puppet"
>>> target_start_index = torch.tensor([14])
>>> target_end_index = torch.tensor([15])

>>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
>>> loss = outputs.loss
>>> round(loss.item(), 2)
...