Skip to content

GitLab

Commit cd77c750 authored by Lysandre's avatar Lysandre Committed by Lysandre Debut
Browse files

BERT PyTorch models

parent 3922a249
Show whitespace changes
Inline Side-by-side
Showing with 395 additions and 335 deletions
docs/source/model_doc/bert.rst
View file @ cd77c750
BERT
----------------------------------------------------
``BertConfig``
Overview
~~~~~~~~~~~~~~~~~~~~~
The BERT model was proposed in `BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding <https://arxiv.org/abs/1810.04805>`__
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.
The abstract from the paper is the following:
*We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations
from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional
representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result,
the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models
for a wide range of tasks, such as question answering and language inference, without substantial task-specific
architecture modifications.*
*BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural
language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI
accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute
improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).*
Tips:
- BERT is a model with absolute position embeddings so it's usually advised to pad the inputs on
the right rather than the left.
BertConfig
~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertConfig
:members:
``BertTokenizer``
BertTokenizer
~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertTokenizer
:members:
``BertModel``
BertModel
~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertModel
:members:
``BertForPreTraining``
BertForPreTraining
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertForPreTraining
:members:
``BertForMaskedLM``
BertForMaskedLM
~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertForMaskedLM
:members:
``BertForNextSentencePrediction``
BertForNextSentencePrediction
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertForNextSentencePrediction
:members:
``BertForSequenceClassification``
BertForSequenceClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertForSequenceClassification
:members:
``BertForMultipleChoice``
BertForMultipleChoice
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertForMultipleChoice
:members:
``BertForTokenClassification``
BertForTokenClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertForTokenClassification
:members:
``BertForQuestionAnswering``
BertForQuestionAnswering
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.BertForQuestionAnswering
:members:
``TFBertModel``
TFBertModel
~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFBertModel
:members:
``TFBertForPreTraining``
TFBertForPreTraining
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFBertForPreTraining
:members:
``TFBertForMaskedLM``
TFBertForMaskedLM
~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFBertForMaskedLM
:members:
``TFBertForNextSentencePrediction``
TFBertForNextSentencePrediction
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFBertForNextSentencePrediction
:members:
``TFBertForSequenceClassification``
TFBertForSequenceClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFBertForSequenceClassification
:members:
``TFBertForMultipleChoice``
TFBertForMultipleChoice
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFBertForMultipleChoice
:members:
``TFBertForTokenClassification``
TFBertForTokenClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFBertForTokenClassification
:members:
``TFBertForQuestionAnswering``
TFBertForQuestionAnswering
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFBertForQuestionAnswering
......
src/transformers/modeling_albert.py
View file @ cd77c750
......@@ -645,7 +645,7 @@ class AlbertForMaskedLM(AlbertPreTrainedModel):
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.AlbertConfig`) 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 (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`)
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
......
src/transformers/modeling_bert.py
View file @ cd77c750
......@@ -25,7 +25,7 @@ from torch import nn
from torch.nn import CrossEntropyLoss, MSELoss
from .configuration_bert import BertConfig
from .file_utils import add_start_docstrings
from .file_utils import add_start_docstrings, add_start_docstrings_to_callable
from .modeling_utils import PreTrainedModel, prune_linear_layer
......@@ -545,12 +545,7 @@ class BertPreTrainedModel(PreTrainedModel):
module.bias.data.zero_()
BERT_START_DOCSTRING = r""" 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.
BERT_START_DOCSTRING = r"""
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.
......@@ -567,53 +562,44 @@ BERT_START_DOCSTRING = r""" The BERT model was proposed in
"""
BERT_INPUTS_DOCSTRING = r"""
Inputs:
**input_ids**: ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
Args:
input_ids (:obj:`torch.LongTensor` of shape :obj:`(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:
(a) 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``
(b) 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 :class:`transformers.BertTokenizer`.
See :func:`transformers.PreTrainedTokenizer.encode` and
:func:`transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
**attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``:
:func:`transformers.PreTrainedTokenizer.encode_plus` for details.
`What are input IDs? <../glossary.html#input-ids>`__
attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`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.
**token_type_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
`What are attention masks? <../glossary.html#attention-mask>`__
token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
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)``:
`What are token type IDs? <../glossary.html#token-type-ids>`_
position_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
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)``:
`What are position IDs? <../glossary.html#position-ids>`_
head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`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**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, embedding_dim)``:
Optionally, instead of passing ``input_ids`` you can choose to directly pass an embedded representation.
:obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
input_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
Optionally, instead of passing :obj:`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.
**encoder_hidden_states**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, hidden_size)``:
Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model
is configured as a decoder.
**encoder_attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``:
encoder_hidden_states (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
if the model is configured as a decoder.
encoder_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
Mask to avoid performing attention on the padding token indices of the encoder input. This mask
is used in the cross-attention if the model is configured as a decoder.
Mask values selected in ``[0, 1]``:
......@@ -624,35 +610,21 @@ BERT_INPUTS_DOCSTRING = r"""
@add_start_docstrings(
"The bare Bert Model transformer outputting raw hidden-states without any specific head on top.",
BERT_START_DOCSTRING,
BERT_INPUTS_DOCSTRING,
)
class BertModel(BertPreTrainedModel):
r"""
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::
The model can behave as an encoder (with only self-attention) as well
as a decoder, in which case a layer of cross-attention is added between
the self-attention layers, following the architecture described in `Attention is all you need`_ by Ashish Vaswani,
Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.
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", add_special_tokens=True)).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
To behave as an decoder the model needs to be initialized with the
:obj:`is_decoder` argument of the configuration set to :obj:`True`; an
:obj:`encoder_hidden_states` is expected as an input to the forward pass.
.. _`Attention is all you need`:
https://arxiv.org/abs/1706.03762
"""
......@@ -680,6 +652,7 @@ class BertModel(BertPreTrainedModel):
for layer, heads in heads_to_prune.items():
self.encoder.layer[layer].attention.prune_heads(heads)
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
......@@ -691,21 +664,42 @@ class BertModel(BertPreTrainedModel):
encoder_hidden_states=None,
encoder_attention_mask=None,
):
""" Forward pass on the Model.
r"""
Return:
:obj:`Tuple` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
last_hidden_state (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
pooler_output (:obj:`torch.FloatTensor`: of shape :obj:`(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 pre-training.
The model can behave as an encoder (with only self-attention) as well
as a decoder, in which case a layer of cross-attention is added between
the self-attention layers, following the architecture described in `Attention is all you need`_ by Ashish Vaswani,
Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.
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 (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
To behave as an decoder the model needs to be initialized with the
`is_decoder` argument of the configuration set to `True`; an
`encoder_hidden_states` is expected as an input to the forward pass.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(batch_size, num_heads, sequence_length, sequence_length)`.
.. _`Attention is all you need`:
https://arxiv.org/abs/1706.03762
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", add_special_tokens=True)).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
"""
if input_ids is not None and inputs_embeds is not None:
raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
elif input_ids is not None:
......@@ -820,48 +814,11 @@ class BertModel(BertPreTrainedModel):
@add_start_docstrings(
"""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. """,
"""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. """,
BERT_START_DOCSTRING,
BERT_INPUTS_DOCSTRING,
)
class BertForPreTraining(BertPreTrainedModel):
r"""
**masked_lm_labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
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]``
**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", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids)
prediction_scores, seq_relationship_scores = outputs[:2]
"""
def __init__(self, config):
super().__init__(config)
......@@ -874,6 +831,7 @@ class BertForPreTraining(BertPreTrainedModel):
def get_output_embeddings(self):
return self.cls.predictions.decoder
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
......@@ -885,6 +843,49 @@ class BertForPreTraining(BertPreTrainedModel):
masked_lm_labels=None,
next_sentence_label=None,
):
r"""
masked_lm_labels (``torch.LongTensor`` of shape ``(batch_size, sequence_length)``, `optional`, defaults to :obj:`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]``
next_sentence_label (``torch.LongTensor`` of shape ``(batch_size,)``, `optional`, defaults to :obj:`None`):
Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair (see :obj:`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.
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
loss (`optional`, returned when ``masked_lm_labels`` is 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 (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`)
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
seq_relationship_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, 2)`):
Prediction scores of the next sequence prediction (classification) head (scores of True/False
continuation before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(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", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids)
prediction_scores, seq_relationship_scores = outputs[:2]
"""
outputs = self.bert(
input_ids,
......@@ -913,45 +914,9 @@ class BertForPreTraining(BertPreTrainedModel):
@add_start_docstrings(
"""Bert Model with a `language modeling` head on top. """, BERT_START_DOCSTRING, BERT_INPUTS_DOCSTRING
"""Bert Model with a `language modeling` head on top. """, BERT_START_DOCSTRING
)
class BertForMaskedLM(BertPreTrainedModel):
r"""
**masked_lm_labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
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]``
**lm_labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
Labels for computing the left-to-right language modeling loss (next word prediction).
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]``
Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
**masked_lm_loss**: (`optional`, returned when ``masked_lm_labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
Masked language modeling loss.
**ltr_lm_loss**: (`optional`, returned when ``lm_labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
Next token prediction 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", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids, masked_lm_labels=input_ids)
loss, prediction_scores = outputs[:2]
"""
def __init__(self, config):
super().__init__(config)
......@@ -964,6 +929,7 @@ class BertForMaskedLM(BertPreTrainedModel):
def get_output_embeddings(self):
return self.cls.predictions.decoder
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
......@@ -977,6 +943,47 @@ class BertForMaskedLM(BertPreTrainedModel):
encoder_attention_mask=None,
lm_labels=None,
):
r"""
masked_lm_labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`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]``
lm_labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
Labels for computing the left-to-right language modeling loss (next word prediction).
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]``
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
masked_lm_loss (`optional`, returned when ``masked_lm_labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
Masked language modeling loss.
ltr_lm_loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`lm_labels` is provided):
Next token prediction loss.
prediction_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`)
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(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", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids, masked_lm_labels=input_ids)
loss, prediction_scores = outputs[:2]
"""
outputs = self.bert(
input_ids,
......@@ -1019,38 +1026,8 @@ class BertForMaskedLM(BertPreTrainedModel):
@add_start_docstrings(
"""Bert Model with a `next sentence prediction (classification)` head on top. """,
BERT_START_DOCSTRING,
BERT_INPUTS_DOCSTRING,
)
class BertForNextSentencePrediction(BertPreTrainedModel):
r"""
**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", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids)
seq_relationship_scores = outputs[0]
"""
def __init__(self, config):
super().__init__(config)
......@@ -1060,6 +1037,7 @@ class BertForNextSentencePrediction(BertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
......@@ -1070,6 +1048,40 @@ class BertForNextSentencePrediction(BertPreTrainedModel):
inputs_embeds=None,
next_sentence_label=None,
):
r"""
next_sentence_label (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
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.
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`next_sentence_label` is provided):
Next sequence prediction (classification) loss.
seq_relationship_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, 2)`):
Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(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", add_special_tokens=True)).unsqueeze(0) # Batch size 1
outputs = model(input_ids)
seq_relationship_scores = outputs[0]
"""
outputs = self.bert(
input_ids,
......@@ -1097,39 +1109,8 @@ class BertForNextSentencePrediction(BertPreTrainedModel):
"""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. """,
BERT_START_DOCSTRING,
BERT_INPUTS_DOCSTRING,
)
class BertForSequenceClassification(BertPreTrainedModel):
r"""
**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", add_special_tokens=True)).unsqueeze(0) # Batch size 1
labels = torch.tensor([1]).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)
loss, logits = outputs[:2]
"""
def __init__(self, config):
super().__init__(config)
......@@ -1141,6 +1122,7 @@ class BertForSequenceClassification(BertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
......@@ -1151,6 +1133,41 @@ class BertForSequenceClassification(BertPreTrainedModel):
inputs_embeds=None,
labels=None,
):
r"""
labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
Labels for computing the sequence classification/regression loss.
Indices should be in :obj:`[0, ..., config.num_labels - 1]`.
If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`label` is provided):
Classification (or regression if config.num_labels==1) loss.
logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, config.num_labels)`):
Classification (or regression if config.num_labels==1) scores (before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(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", add_special_tokens=True)).unsqueeze(0) # Batch size 1
labels = torch.tensor([1]).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)
loss, logits = outputs[:2]
"""
outputs = self.bert(
input_ids,
......@@ -1185,40 +1202,8 @@ class BertForSequenceClassification(BertPreTrainedModel):
"""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. """,
BERT_START_DOCSTRING,
BERT_INPUTS_DOCSTRING,
)
class BertForMultipleChoice(BertPreTrainedModel):
r"""
**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, add_special_tokens=True) 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]
"""
def __init__(self, config):
super().__init__(config)
......@@ -1229,6 +1214,7 @@ class BertForMultipleChoice(BertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
......@@ -1239,6 +1225,43 @@ class BertForMultipleChoice(BertPreTrainedModel):
inputs_embeds=None,
labels=None,
):
r"""
labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
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)
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (config) and inputs:
loss (:obj:`torch.FloatTensor`` of shape ``(1,)`, `optional`, returned when :obj:`labels` is provided):
Classification loss.
classification_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, num_choices)`):
`num_choices` is the second dimension of the input tensors. (see `input_ids` above).
Classification scores (before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(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, add_special_tokens=True) 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]
"""
num_choices = input_ids.shape[1]
input_ids = input_ids.view(-1, input_ids.size(-1))
......@@ -1275,37 +1298,8 @@ class BertForMultipleChoice(BertPreTrainedModel):
"""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. """,
BERT_START_DOCSTRING,
BERT_INPUTS_DOCSTRING,
)
class BertForTokenClassification(BertPreTrainedModel):
r"""
**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", add_special_tokens=True)).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]
"""
def __init__(self, config):
super().__init__(config)
......@@ -1317,6 +1311,7 @@ class BertForTokenClassification(BertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
......@@ -1327,6 +1322,39 @@ class BertForTokenClassification(BertPreTrainedModel):
inputs_embeds=None,
labels=None,
):
r"""
labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`, defaults to :obj:`None`):
Labels for computing the token classification loss.
Indices should be in ``[0, ..., config.num_labels - 1]``.
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:obj:`~transformers.BertConfig`) and inputs:
loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when ``labels`` is provided) :
Classification loss.
scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.num_labels)`)
Classification scores (before SoftMax).
hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(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", add_special_tokens=True)).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]
"""
outputs = self.bert(
input_ids,
......@@ -1359,36 +1387,62 @@ class BertForTokenClassification(BertPreTrainedModel):
@add_start_docstrings(
"""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`). """,
"""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`). """,
BERT_START_DOCSTRING,
BERT_INPUTS_DOCSTRING,
)
class BertForQuestionAnswering(BertPreTrainedModel):
def __init__(self, config):
super(BertForQuestionAnswering, self).__init__(config)
self.num_labels = config.num_labels
self.bert = BertModel(config)
self.qa_outputs = nn.Linear(config.hidden_size, config.num_labels)
self.init_weights()
@add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
attention_mask=None,
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
start_positions=None,
end_positions=None,
):
r"""
**start_positions**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
start_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`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**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
end_positions (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`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.
Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
**loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
Returns:
:obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (config) and inputs:
loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`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,)``
start_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length,)`):
Span-start scores (before SoftMax).
**end_scores**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length,)``
end_scores (:obj:`torch.FloatTensor` of shape :obj:`(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 (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_hidden_states=True``):
Tuple of :obj:`torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer)
of shape :obj:`(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.
attentions (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``config.output_attentions=True``):
Tuple of :obj:`torch.FloatTensor` (one for each layer) of shape
:obj:`(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::
......@@ -1402,30 +1456,8 @@ class BertForQuestionAnswering(BertPreTrainedModel):
print(' '.join(all_tokens[torch.argmax(start_scores) : torch.argmax(end_scores)+1]))
# a nice puppet
"""
def __init__(self, config):
super().__init__(config)
self.num_labels = config.num_labels
self.bert = BertModel(config)
self.qa_outputs = nn.Linear(config.hidden_size, config.num_labels)
self.init_weights()
def forward(
self,
input_ids=None,
attention_mask=None,
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
start_positions=None,
end_positions=None,
):
outputs = self.bert(
input_ids,
attention_mask=attention_mask,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment