BERT

BertConfig

class pytorch_transformers.BertConfig(vocab_size_or_config_json_file=30522, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act='gelu', hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, **kwargs)[source]

BertConfig is the configuration class to store the configuration of a BertModel.

Parameters
  • vocab_size_or_config_json_file – Vocabulary size of inputs_ids in BertModel.

  • hidden_size – Size of the encoder layers and the pooler layer.

  • num_hidden_layers – Number of hidden layers in the Transformer encoder.

  • num_attention_heads – Number of attention heads for each attention layer in the Transformer encoder.

  • intermediate_size – The size of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.

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

  • hidden_dropout_prob – The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.

  • attention_probs_dropout_prob – The dropout ratio for the attention probabilities.

  • max_position_embeddings – 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).

  • type_vocab_size – The vocabulary size of the token_type_ids passed into BertModel.

  • initializer_range – The sttdev of the truncated_normal_initializer for initializing all weight matrices.

  • layer_norm_eps – The epsilon used by LayerNorm.

BertTokenizer

class pytorch_transformers.BertTokenizer(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)[source]

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

Parameters
  • vocab_file – Path to a one-wordpiece-per-line vocabulary file

  • do_lower_case – Whether to lower case the input. Only has an effect when do_wordpiece_only=False

  • do_basic_tokenize – Whether to do basic tokenization before wordpiece.

  • max_len – An artificial maximum length to truncate tokenized sequences to; Effective maximum length is always the minimum of this value (if specified) and the underlying BERT model’s sequence length.

  • never_split – List of tokens which will never be split during tokenization. Only has an effect when do_wordpiece_only=False

add_special_tokens_sentences_pair(token_ids_0, token_ids_1)[source]

Adds special tokens to a sequence pair for sequence classification tasks. A BERT sequence pair has the following format: [CLS] A [SEP] B [SEP]

add_special_tokens_single_sentence(token_ids)[source]

Adds special tokens to the a sequence for sequence classification tasks. A BERT sequence has the following format: [CLS] X [SEP]

convert_tokens_to_string(tokens)[source]

Converts a sequence of tokens (string) in a single string.

save_vocabulary(vocab_path)[source]

Save the tokenizer vocabulary to a directory or file.

property vocab_size

Size of the base vocabulary (without the added tokens)

BertModel

class pytorch_transformers.BertModel(config)[source]

The bare Bert Model transformer outputting raw hidden-states without any specific head on top. The BERT model was proposed in BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It’s a bidirectional transformer pre-trained using a combination of masked language modeling objective and next sentence prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.

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 (BertConfig) – 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.

Inputs:
input_ids: torch.LongTensor of shape (batch_size, sequence_length):

Indices of input sequence tokens in the vocabulary. To match pre-training, BERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:

  1. For sequence pairs:

    tokens:         [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]

    token_type_ids:   0   0  0    0    0     0       0   0   1  1  1  1   1   1

  2. For single sequences:

    tokens:         [CLS] the dog is hairy . [SEP]

    token_type_ids:   0   0   0   0  0     0   0

Bert is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

Indices can be obtained using pytorch_transformers.BertTokenizer. See pytorch_transformers.PreTrainedTokenizer.encode() and pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids() for details.

attention_mask: (optional) torch.FloatTensor of shape (batch_size, sequence_length):

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.

token_type_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]: 0 corresponds to a sentence A token, 1 corresponds to a sentence B token (see BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding for more details).

position_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

head_mask: (optional) torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads):

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.

Outputs: Tuple comprising various elements depending on the configuration (config) and inputs:
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.

pooler_output: torch.FloatTensor of shape (batch_size, hidden_size)

Last layer hidden-state of the first token of the sequence (classification token) further processed by a Linear layer and a Tanh activation function. The Linear layer weights are trained from the next sentence prediction (classification) objective during Bert pretraining. This output is usually not a good summary of the semantic content of the input, you’re often better with averaging or pooling the sequence of hidden-states for the whole input sequence.

hidden_states: (optional, returned when config.output_hidden_states=True)

list of torch.FloatTensor (one for the output of each layer + the output of the embeddings) 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: (optional, returned when config.output_attentions=True)

list 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.

Examples:

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertModel.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
outputs = model(input_ids)
last_hidden_states = outputs[0]  # The last hidden-state is the first element of the output tuple
forward(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.

BertForPreTraining

class pytorch_transformers.BertForPreTraining(config)[source]

Bert Model with two heads on top as done during the pre-training: a masked language modeling head and a next sentence prediction (classification) head. The BERT model was proposed in BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It’s a bidirectional transformer pre-trained using a combination of masked language modeling objective and next sentence prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.

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 (BertConfig) – 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.

Inputs:
input_ids: torch.LongTensor of shape (batch_size, sequence_length):

Indices of input sequence tokens in the vocabulary. To match pre-training, BERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:

  1. For sequence pairs:

    tokens:         [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]

    token_type_ids:   0   0  0    0    0     0       0   0   1  1  1  1   1   1

  2. For single sequences:

    tokens:         [CLS] the dog is hairy . [SEP]

    token_type_ids:   0   0   0   0  0     0   0

Bert is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

Indices can be obtained using pytorch_transformers.BertTokenizer. See pytorch_transformers.PreTrainedTokenizer.encode() and pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids() for details.

attention_mask: (optional) torch.FloatTensor of shape (batch_size, sequence_length):

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.

token_type_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]: 0 corresponds to a sentence A token, 1 corresponds to a sentence B token (see BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding for more details).

position_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

head_mask: (optional) torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads):

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.

masked_lm_labels: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Labels for computing the masked language modeling loss. Indices should be in [-1, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -1 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

next_sentence_label: (optional) torch.LongTensor of shape (batch_size,):

Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair (see input_ids docstring) Indices should be in [0, 1]. 0 indicates sequence B is a continuation of sequence A, 1 indicates sequence B is a random sequence.

Outputs: Tuple comprising various elements depending on the configuration (config) and inputs:
loss: (optional, returned when both masked_lm_labels and next_sentence_label are provided) torch.FloatTensor of shape (1,):

Total loss as the sum of the masked language modeling loss and the next sequence prediction (classification) 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).

seq_relationship_scores: torch.FloatTensor of shape (batch_size, sequence_length, 2)

Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax).

hidden_states: (optional, returned when config.output_hidden_states=True)

list of torch.FloatTensor (one for the output of each layer + the output of the embeddings) 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: (optional, returned when config.output_attentions=True)

list 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.

Examples:

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForPreTraining.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
outputs = model(input_ids)
prediction_scores, seq_relationship_scores = outputs[:2]
forward(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, masked_lm_labels=None, next_sentence_label=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.

tie_weights()[source]

Make sure we are sharing the input and output embeddings. Export to TorchScript can’t handle parameter sharing so we are cloning them instead.

BertForMaskedLM

class pytorch_transformers.BertForMaskedLM(config)[source]

Bert Model with a language modeling head on top. The BERT model was proposed in BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It’s a bidirectional transformer pre-trained using a combination of masked language modeling objective and next sentence prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.

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 (BertConfig) – 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.

Inputs:
input_ids: torch.LongTensor of shape (batch_size, sequence_length):

Indices of input sequence tokens in the vocabulary. To match pre-training, BERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:

  1. For sequence pairs:

    tokens:         [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]

    token_type_ids:   0   0  0    0    0     0       0   0   1  1  1  1   1   1

  2. For single sequences:

    tokens:         [CLS] the dog is hairy . [SEP]

    token_type_ids:   0   0   0   0  0     0   0

Bert is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

Indices can be obtained using pytorch_transformers.BertTokenizer. See pytorch_transformers.PreTrainedTokenizer.encode() and pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids() for details.

attention_mask: (optional) torch.FloatTensor of shape (batch_size, sequence_length):

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.

token_type_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]: 0 corresponds to a sentence A token, 1 corresponds to a sentence B token (see BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding for more details).

position_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

head_mask: (optional) torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads):

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.

masked_lm_labels: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Labels for computing the masked language modeling loss. Indices should be in [-1, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -1 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size]

Outputs: Tuple comprising various elements depending on the configuration (config) and inputs:
loss: (optional, returned when masked_lm_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: (optional, returned when config.output_hidden_states=True)

list of torch.FloatTensor (one for the output of each layer + the output of the embeddings) 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: (optional, returned when config.output_attentions=True)

list 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.

Examples:

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForMaskedLM.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
outputs = model(input_ids, masked_lm_labels=input_ids)
loss, prediction_scores = outputs[:2]
forward(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, masked_lm_labels=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.

tie_weights()[source]

Make sure we are sharing the input and output embeddings. Export to TorchScript can’t handle parameter sharing so we are cloning them instead.

BertForNextSentencePrediction

class pytorch_transformers.BertForNextSentencePrediction(config)[source]

Bert Model with a next sentence prediction (classification) head on top. The BERT model was proposed in BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It’s a bidirectional transformer pre-trained using a combination of masked language modeling objective and next sentence prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.

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 (BertConfig) – 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.

Inputs:
input_ids: torch.LongTensor of shape (batch_size, sequence_length):

Indices of input sequence tokens in the vocabulary. To match pre-training, BERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:

  1. For sequence pairs:

    tokens:         [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]

    token_type_ids:   0   0  0    0    0     0       0   0   1  1  1  1   1   1

  2. For single sequences:

    tokens:         [CLS] the dog is hairy . [SEP]

    token_type_ids:   0   0   0   0  0     0   0

Bert is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

Indices can be obtained using pytorch_transformers.BertTokenizer. See pytorch_transformers.PreTrainedTokenizer.encode() and pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids() for details.

attention_mask: (optional) torch.FloatTensor of shape (batch_size, sequence_length):

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.

token_type_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]: 0 corresponds to a sentence A token, 1 corresponds to a sentence B token (see BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding for more details).

position_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

head_mask: (optional) torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads):

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.

next_sentence_label: (optional) torch.LongTensor of shape (batch_size,):

Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair (see input_ids docstring) Indices should be in [0, 1]. 0 indicates sequence B is a continuation of sequence A, 1 indicates sequence B is a random sequence.

Outputs: Tuple comprising various elements depending on the configuration (config) and inputs:
loss: (optional, returned when next_sentence_label is provided) torch.FloatTensor of shape (1,):

Next sequence prediction (classification) loss.

seq_relationship_scores: torch.FloatTensor of shape (batch_size, sequence_length, 2)

Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax).

hidden_states: (optional, returned when config.output_hidden_states=True)

list of torch.FloatTensor (one for the output of each layer + the output of the embeddings) 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: (optional, returned when config.output_attentions=True)

list 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.

Examples:

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForNextSentencePrediction.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
outputs = model(input_ids)
seq_relationship_scores = outputs[0]
forward(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, next_sentence_label=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.

BertForSequenceClassification

class pytorch_transformers.BertForSequenceClassification(config)[source]

Bert Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks. The BERT model was proposed in BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It’s a bidirectional transformer pre-trained using a combination of masked language modeling objective and next sentence prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.

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 (BertConfig) – 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.

Inputs:
input_ids: torch.LongTensor of shape (batch_size, sequence_length):

Indices of input sequence tokens in the vocabulary. To match pre-training, BERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:

  1. For sequence pairs:

    tokens:         [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]

    token_type_ids:   0   0  0    0    0     0       0   0   1  1  1  1   1   1

  2. For single sequences:

    tokens:         [CLS] the dog is hairy . [SEP]

    token_type_ids:   0   0   0   0  0     0   0

Bert is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

Indices can be obtained using pytorch_transformers.BertTokenizer. See pytorch_transformers.PreTrainedTokenizer.encode() and pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids() for details.

attention_mask: (optional) torch.FloatTensor of shape (batch_size, sequence_length):

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.

token_type_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]: 0 corresponds to a sentence A token, 1 corresponds to a sentence B token (see BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding for more details).

position_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

head_mask: (optional) torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads):

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.

labels: (optional) torch.LongTensor of shape (batch_size,):

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).

Outputs: Tuple comprising various elements depending on the configuration (config) and inputs:
loss: (optional, returned when labels is provided) torch.FloatTensor of shape (1,):

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: (optional, returned when config.output_hidden_states=True)

list of torch.FloatTensor (one for the output of each layer + the output of the embeddings) 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: (optional, returned when config.output_attentions=True)

list 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.

Examples:

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
outputs = model(input_ids, labels=labels)
loss, logits = outputs[:2]
forward(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, labels=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.

BertForMultipleChoice

class pytorch_transformers.BertForMultipleChoice(config)[source]

Bert Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks. The BERT model was proposed in BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It’s a bidirectional transformer pre-trained using a combination of masked language modeling objective and next sentence prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.

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 (BertConfig) – 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.

Inputs:
input_ids: torch.LongTensor of shape (batch_size, sequence_length):

Indices of input sequence tokens in the vocabulary. To match pre-training, BERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:

  1. For sequence pairs:

    tokens:         [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]

    token_type_ids:   0   0  0    0    0     0       0   0   1  1  1  1   1   1

  2. For single sequences:

    tokens:         [CLS] the dog is hairy . [SEP]

    token_type_ids:   0   0   0   0  0     0   0

Bert is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

Indices can be obtained using pytorch_transformers.BertTokenizer. See pytorch_transformers.PreTrainedTokenizer.encode() and pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids() for details.

attention_mask: (optional) torch.FloatTensor of shape (batch_size, sequence_length):

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.

token_type_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]: 0 corresponds to a sentence A token, 1 corresponds to a sentence B token (see BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding for more details).

position_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

head_mask: (optional) torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads):

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.

labels: (optional) torch.LongTensor of shape (batch_size,):

Labels for computing the multiple choice classification loss. Indices should be in [0, ..., num_choices] where num_choices is the size of the second dimension of the input tensors. (see input_ids above)

Outputs: Tuple comprising various elements depending on the configuration (config) and inputs:
loss: (optional, returned when labels is provided) torch.FloatTensor of shape (1,):

Classification loss.

classification_scores: torch.FloatTensor of shape (batch_size, num_choices) where num_choices is the size of the second dimension

of the input tensors. (see input_ids above). Classification scores (before SoftMax).

hidden_states: (optional, returned when config.output_hidden_states=True)

list of torch.FloatTensor (one for the output of each layer + the output of the embeddings) 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: (optional, returned when config.output_attentions=True)

list 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.

Examples:

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForMultipleChoice.from_pretrained('bert-base-uncased')
choices = ["Hello, my dog is cute", "Hello, my cat is amazing"]
input_ids = torch.tensor([tokenizer.encode(s) for s in choices]).unsqueeze(0)  # Batch size 1, 2 choices
labels = torch.tensor(1).unsqueeze(0)  # Batch size 1
outputs = model(input_ids, labels=labels)
loss, classification_scores = outputs[:2]
forward(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, labels=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.

BertForTokenClassification

class pytorch_transformers.BertForTokenClassification(config)[source]

Bert Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks. The BERT model was proposed in BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It’s a bidirectional transformer pre-trained using a combination of masked language modeling objective and next sentence prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.

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 (BertConfig) – 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.

Inputs:
input_ids: torch.LongTensor of shape (batch_size, sequence_length):

Indices of input sequence tokens in the vocabulary. To match pre-training, BERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:

  1. For sequence pairs:

    tokens:         [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]

    token_type_ids:   0   0  0    0    0     0       0   0   1  1  1  1   1   1

  2. For single sequences:

    tokens:         [CLS] the dog is hairy . [SEP]

    token_type_ids:   0   0   0   0  0     0   0

Bert is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

Indices can be obtained using pytorch_transformers.BertTokenizer. See pytorch_transformers.PreTrainedTokenizer.encode() and pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids() for details.

attention_mask: (optional) torch.FloatTensor of shape (batch_size, sequence_length):

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.

token_type_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]: 0 corresponds to a sentence A token, 1 corresponds to a sentence B token (see BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding for more details).

position_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

head_mask: (optional) torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads):

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.

labels: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Labels for computing the token classification loss. Indices should be in [0, ..., config.num_labels - 1].

Outputs: Tuple comprising various elements depending on the configuration (config) and inputs:
loss: (optional, returned when labels is provided) torch.FloatTensor of shape (1,):

Classification loss.

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

Classification scores (before SoftMax).

hidden_states: (optional, returned when config.output_hidden_states=True)

list of torch.FloatTensor (one for the output of each layer + the output of the embeddings) 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: (optional, returned when config.output_attentions=True)

list 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.

Examples:

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForTokenClassification.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
labels = torch.tensor([1] * input_ids.size(1)).unsqueeze(0)  # Batch size 1
outputs = model(input_ids, labels=labels)
loss, scores = outputs[:2]
forward(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, labels=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.

BertForQuestionAnswering

class pytorch_transformers.BertForQuestionAnswering(config)[source]

Bert 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). The BERT model was proposed in BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It’s a bidirectional transformer pre-trained using a combination of masked language modeling objective and next sentence prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.

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 (BertConfig) – 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.

Inputs:
input_ids: torch.LongTensor of shape (batch_size, sequence_length):

Indices of input sequence tokens in the vocabulary. To match pre-training, BERT input sequence should be formatted with [CLS] and [SEP] tokens as follows:

  1. For sequence pairs:

    tokens:         [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]

    token_type_ids:   0   0  0    0    0     0       0   0   1  1  1  1   1   1

  2. For single sequences:

    tokens:         [CLS] the dog is hairy . [SEP]

    token_type_ids:   0   0   0   0  0     0   0

Bert is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.

Indices can be obtained using pytorch_transformers.BertTokenizer. See pytorch_transformers.PreTrainedTokenizer.encode() and pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids() for details.

attention_mask: (optional) torch.FloatTensor of shape (batch_size, sequence_length):

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.

token_type_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]: 0 corresponds to a sentence A token, 1 corresponds to a sentence B token (see BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding for more details).

position_ids: (optional) torch.LongTensor of shape (batch_size, sequence_length):

Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

head_mask: (optional) torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads):

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.

start_positions: (optional) torch.LongTensor of shape (batch_size,):

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: (optional) torch.LongTensor of shape (batch_size,):

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.

Outputs: Tuple comprising various elements depending on the configuration (config) and inputs:
loss: (optional, returned when labels is provided) torch.FloatTensor of shape (1,):

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: (optional, returned when config.output_hidden_states=True)

list of torch.FloatTensor (one for the output of each layer + the output of the embeddings) 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: (optional, returned when config.output_attentions=True)

list 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.

Examples:

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForQuestionAnswering.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
start_positions = torch.tensor([1])
end_positions = torch.tensor([3])
outputs = model(input_ids, start_positions=start_positions, end_positions=end_positions)
loss, start_scores, end_scores = outputs[:2]
forward(input_ids, attention_mask=None, token_type_ids=None, position_ids=None, head_mask=None, start_positions=None, end_positions=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

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 registered hooks while the latter silently ignores them.