DistilBERT

The DistilBERT model was proposed in the blog post Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT, and the paper DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. DistilBERT is a small, fast, cheap and light Transformer model trained by distilling Bert base. It has 40% less parameters than bert-base-uncased, runs 60% faster while preserving over 95% of Bert’s performances as measured on the GLUE language understanding benchmark.

Note

This class is nearly identical to the PyTorch implementation of DistilBERT in Huggingface Transformers. For more information, visit the corresponding section in their documentation.

DistilBertConfig

class transformers.DistilBertConfig(vocab_size=30522, max_position_embeddings=512, sinusoidal_pos_embds=False, n_layers=6, n_heads=12, dim=768, hidden_dim=3072, dropout=0.1, attention_dropout=0.1, activation='gelu', initializer_range=0.02, qa_dropout=0.1, seq_classif_dropout=0.2, pad_token_id=0, **kwargs)

This is the configuration class to store the configuration of a DistilBertModel. It is used to instantiate a DistilBERT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the DistilBERT distilbert-base-uncased architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Parameters
  • vocab_size (int, optional, defaults to 30522) – Vocabulary size of the DistilBERT model. Defines the different tokens that can be represented by the inputs_ids passed to the forward method of BertModel.

  • max_position_embeddings (int, optional, defaults to 512) – The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).

  • sinusoidal_pos_embds (boolean, optional, defaults to False) – Whether to use sinusoidal positional embeddings.

  • n_layers (int, optional, defaults to 6) – Number of hidden layers in the Transformer encoder.

  • n_heads (int, optional, defaults to 12) – Number of attention heads for each attention layer in the Transformer encoder.

  • dim (int, optional, defaults to 768) – Dimensionality of the encoder layers and the pooler layer.

  • hidden_dim (int, optional, defaults to 3072) – The size of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.

  • dropout (float, optional, defaults to 0.1) – The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.

  • attention_dropout (float, optional, defaults to 0.1) – The dropout ratio for the attention probabilities.

  • activation (str or function, optional, defaults to “gelu”) – The non-linear activation function (function or string) in the encoder and pooler. If string, “gelu”, “relu”, “swish” and “gelu_new” are supported.

  • initializer_range (float, optional, defaults to 0.02) – The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

  • qa_dropout (float, optional, defaults to 0.1) – The dropout probabilities used in the question answering model DistilBertForQuestionAnswering.

  • seq_classif_dropout (float, optional, defaults to 0.2) – The dropout probabilities used in the sequence classification and the multiple choice model DistilBertForSequenceClassification.

Example:

>>> from transformers import DistilBertModel, DistilBertConfig

>>> # Initializing a DistilBERT configuration
>>> configuration = DistilBertConfig()

>>> # Initializing a model from the configuration
>>> model = DistilBertModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

DistilBertTokenizer

class transformers.DistilBertTokenizer(vocab_file, do_lower_case=True, do_basic_tokenize=True, never_split=None, unk_token='[UNK]', sep_token='[SEP]', pad_token='[PAD]', cls_token='[CLS]', mask_token='[MASK]', tokenize_chinese_chars=True, **kwargs)

Constructs a DistilBertTokenizer.

BertTokenizer and runs end-to-end tokenization: punctuation splitting + wordpiece.

Refer to superclass BertTokenizer for usage examples and documentation concerning parameters.

DistilBertTokenizerFast

class transformers.DistilBertTokenizerFast(vocab_file, do_lower_case=True, unk_token='[UNK]', sep_token='[SEP]', pad_token='[PAD]', cls_token='[CLS]', mask_token='[MASK]', clean_text=True, tokenize_chinese_chars=True, strip_accents=None, wordpieces_prefix='##', **kwargs)

Constructs a “Fast” DistilBertTokenizer (backed by HuggingFace’s tokenizers library).

DistilBertTokenizerFast is identical to BertTokenizerFast and runs end-to-end tokenization: punctuation splitting + wordpiece.

Refer to superclass BertTokenizerFast for usage examples and documentation concerning parameters.

DistilBertModel

class transformers.DistilBertModel(config)

The bare DistilBERT encoder/transformer outputting raw hidden-states without any specific head on top.

This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

Parameters

config (DistilBertConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

forward(input_ids=None, attention_mask=None, head_mask=None, inputs_embeds=None, output_attentions=None, output_hidden_states=None, adapter_names=None)

The DistilBertModel forward method, overrides the __call__() special method.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Parameters
  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –

    Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using transformers.DistilBertTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional, defaults to None) –

    Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]: 1 for tokens that are NOT MASKED, 0 for MASKED tokens.

    What are attention masks?

  • head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional, defaults to None) – Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]: 1 indicates the head is not masked, 0 indicates the head is masked.

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional, defaults to None) – Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

  • output_attentions (bool, optional, defaults to None) – If set to True, the attentions tensors of all attention layers are returned. See attentions under returned tensors for more detail.

Returns

last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)):

Sequence of hidden-states at the output of the last layer of the model.

hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True):

Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the initial embedding outputs.

attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True):

Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

tuple(torch.FloatTensor) comprising various elements depending on the configuration (DistilBertConfig) and inputs

Example:

>>> from transformers import DistilBertTokenizer, DistilBertModel
>>> import torch

>>> tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
>>> model = DistilBertModel.from_pretrained('distilbert-base-uncased')

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

>>> last_hidden_states = outputs[0]  # The last hidden-state is the first element of the output tuple
get_input_embeddings()

Returns the model’s input embeddings.

Returns

A torch module mapping vocabulary to hidden states.

Return type

nn.Module

set_input_embeddings(new_embeddings)

Set model’s input embeddings

Parameters

value (nn.Module) – A module mapping vocabulary to hidden states.

DistilBertModelWithHeads

class transformers.DistilBertModelWithHeads(config)

DistilBert Model transformer with the option to add multiple flexible heads on top.

This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

Parameters

config (DistilBertConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

forward(input_ids=None, attention_mask=None, head_mask=None, inputs_embeds=None, labels=None, adapter_names=None, head=None)

The DistilBertModelWithHeads forward method, overrides the __call__() special method.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Parameters
  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –

    Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using transformers.DistilBertTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional, defaults to None) –

    Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]: 1 for tokens that are NOT MASKED, 0 for MASKED tokens.

    What are attention masks?

  • head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional, defaults to None) – Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]: 1 indicates the head is not masked, 0 indicates the head is masked.

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional, defaults to None) – Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

  • output_attentions (bool, optional, defaults to None) – If set to True, the attentions tensors of all attention layers are returned. See attentions under returned tensors for more detail.

DistilBertForMaskedLM

class transformers.DistilBertForMaskedLM(config)

DistilBert Model with a masked language modeling head on top.

This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

Parameters

config (DistilBertConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

forward(input_ids=None, attention_mask=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, adapter_names=None, **kwargs)

The DistilBertForMaskedLM forward method, overrides the __call__() special method.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Parameters
  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –

    Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using transformers.DistilBertTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional, defaults to None) –

    Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]: 1 for tokens that are NOT MASKED, 0 for MASKED tokens.

    What are attention masks?

  • head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional, defaults to None) – Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]: 1 indicates the head is not masked, 0 indicates the head is masked.

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional, defaults to None) – Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

  • output_attentions (bool, optional, defaults to None) – If set to True, the attentions tensors of all attention layers are returned. See attentions under returned tensors for more detail.

  • labels (torch.LongTensor of shape (batch_size, sequence_length), optional, defaults to None) – Labels for computing the masked language modeling loss. Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

  • kwargs (Dict[str, any], optional, defaults to {}) – Used to hide legacy arguments that have been deprecated.

Returns

loss (optional, returned when labels is provided) torch.FloatTensor of shape (1,):

Masked language modeling loss.

prediction_scores (torch.FloatTensor of shape (batch_size, sequence_length, config.vocab_size))

Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True):

Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the initial embedding outputs.

attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True):

Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

tuple(torch.FloatTensor) comprising various elements depending on the configuration (DistilBertConfig) and inputs

Example:

>>> from transformers import DistilBertTokenizer, DistilBertForMaskedLM
>>> import torch

>>> tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
>>> model = DistilBertForMaskedLM.from_pretrained('distilbert-base-uncased')

>>> input_ids = tokenizer("Hello, my dog is cute", return_tensors="pt")["input_ids"]

>>> outputs = model(input_ids, labels=input_ids)
>>> loss, prediction_scores = outputs[:2]
get_output_embeddings()

Returns the model’s output embeddings.

Returns

A torch module mapping hidden states to vocabulary.

Return type

nn.Module

DistilBertForSequenceClassification

class transformers.DistilBertForSequenceClassification(config)

DistilBert Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

Parameters

config (DistilBertConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

forward(input_ids=None, attention_mask=None, head_mask=None, inputs_embeds=None, labels=None, output_attentions=None, output_hidden_states=None, adapter_names=None)

The DistilBertForSequenceClassification forward method, overrides the __call__() special method.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Parameters
  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –

    Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using transformers.DistilBertTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional, defaults to None) –

    Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]: 1 for tokens that are NOT MASKED, 0 for MASKED tokens.

    What are attention masks?

  • head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional, defaults to None) – Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]: 1 indicates the head is not masked, 0 indicates the head is masked.

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional, defaults to None) – Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

  • output_attentions (bool, optional, defaults to None) – If set to True, the attentions tensors of all attention layers are returned. See attentions under returned tensors for more detail.

  • labels (torch.LongTensor of shape (batch_size,), optional, defaults to None) – Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

Returns

loss (torch.FloatTensor of shape (1,), optional, returned when label is provided):

Classification (or regression if config.num_labels==1) loss.

logits (torch.FloatTensor of shape (batch_size, config.num_labels)):

Classification (or regression if config.num_labels==1) scores (before SoftMax).

hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True):

Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the initial embedding outputs.

attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True):

Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

tuple(torch.FloatTensor) comprising various elements depending on the configuration (DistilBertConfig) and inputs

Example:

>>> from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
>>> import torch

>>> tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
>>> model = DistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
>>> outputs = model(**inputs, labels=labels)
>>> loss, logits = outputs[:2]

DistilBertForQuestionAnswering

class transformers.DistilBertForQuestionAnswering(config)

DistilBert Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of the hidden-states output to compute span start logits and span end logits).

This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

Parameters

config (DistilBertConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

forward(input_ids=None, attention_mask=None, head_mask=None, inputs_embeds=None, start_positions=None, end_positions=None, output_attentions=None, output_hidden_states=None, adapter_names=None)

The DistilBertForQuestionAnswering forward method, overrides the __call__() special method.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Parameters
  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –

    Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using transformers.DistilBertTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional, defaults to None) –

    Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]: 1 for tokens that are NOT MASKED, 0 for MASKED tokens.

    What are attention masks?

  • head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional, defaults to None) – Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]: 1 indicates the head is not masked, 0 indicates the head is masked.

  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional, defaults to None) – Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.

  • output_attentions (bool, optional, defaults to None) – If set to True, the attentions tensors of all attention layers are returned. See attentions under returned tensors for more detail.

  • start_positions (torch.LongTensor of shape (batch_size,), optional, defaults to None) – Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

  • end_positions (torch.LongTensor of shape (batch_size,), optional, defaults to None) – Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.

Returns

loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided):

Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.

start_scores (torch.FloatTensor of shape (batch_size, sequence_length,)):

Span-start scores (before SoftMax).

end_scores (torch.FloatTensor of shape (batch_size, sequence_length,)):

Span-end scores (before SoftMax).

hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True):

Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the initial embedding outputs.

attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True):

Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

Return type

tuple(torch.FloatTensor) comprising various elements depending on the configuration (DistilBertConfig) and inputs

Example:

>>> from transformers import DistilBertTokenizer, DistilBertForQuestionAnswering
>>> import torch

>>> tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
>>> model = DistilBertForQuestionAnswering.from_pretrained('distilbert-base-uncased')

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> start_positions = torch.tensor([1])
>>> end_positions = torch.tensor([3])

>>> outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)
>>> loss, start_scores, end_scores = outputs[:3]