SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

PyTorch DistilBERT

Browse Source
This commit is contained in:
Lysandre
2020-01-20 15:01:36 -05:00
committed by Lysandre Debut
parent b28020f590
commit db1a7f27a1
2 changed files with 209 additions and 177 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
docs/source/model_doc/distilbert.rst
View File

@@ -1,6 +1,23 @@
DistilBERT
----------------------------------------------------
DistilBERT is a small, fast, cheap and light Transformer model
trained by distilling Bert base. It has 40% less parameters than
`bert-base-uncased`, runs 60% faster while preserving over 95% of
Bert's performances as measured on the GLUE language understanding benchmark.
Here are the differences between the interface of Bert and DistilBert:
- DistilBert doesn't have `token_type_ids`, you don't need to indicate which token belongs to which segment. Just separate your segments with the separation token `tokenizer.sep_token` (or `[SEP]`)
- DistilBert doesn't have options to select the input positions (`position_ids` input). This could be added if necessary though, just let's us know if you need this option.
For more information on DistilBERT, please refer to our
`detailed blog post`_
.. _`detailed blog post`:
https://medium.com/huggingface/distilbert-8cf3380435b5
``DistilBertConfig``
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

355
src/transformers/modeling_distilbert.py
View File

@@ -28,7 +28,7 @@ import torch.nn as nn
from torch.nn import CrossEntropyLoss
from .configuration_distilbert import DistilBertConfig
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
@@ -351,21 +351,6 @@ class DistilBertPreTrainedModel(PreTrainedModel):
DISTILBERT_START_DOCSTRING = r"""
DistilBERT is a small, fast, cheap and light Transformer model
trained by distilling Bert base. It has 40% less parameters than
`bert-base-uncased`, runs 60% faster while preserving over 95% of
Bert's performances as measured on the GLUE language understanding benchmark.
Here are the differences between the interface of Bert and DistilBert:
- DistilBert doesn't have `token_type_ids`, you don't need to indicate which token belongs to which segment. Just separate your segments with the separation token `tokenizer.sep_token` (or `[SEP]`)
- DistilBert doesn't have options to select the input positions (`position_ids` input). This could be added if necessary though, just let's us know if you need this option.
For more information on DistilBERT, please refer to our
`detailed blog post`_
.. _`detailed blog post`:
https://medium.com/huggingface/distilbert-8cf3380435b5
Parameters:
config (:class:`~transformers.DistilBertConfig`): Model configuration class with all the parameters of the model.
@@ -374,22 +359,27 @@ DISTILBERT_START_DOCSTRING = r"""
"""
DISTILBERT_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.
The input sequences should start with `[CLS]` and end with `[SEP]` tokens.
For now, ONLY BertTokenizer(`bert-base-uncased`) is supported and you should use this tokenizer when using DistilBERT.
**attention_mask**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
Indices can be obtained using :class:`transformers.DistilBertTokenizer`.
See :func:`transformers.PreTrainedTokenizer.encode` and
: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.
**head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
`What are attention masks? <../glossary.html#attention-mask>`__
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**.
inputs_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.
"""
@@ -398,30 +388,8 @@ DISTILBERT_INPUTS_DOCSTRING = r"""
@add_start_docstrings(
"The bare DistilBERT encoder/transformer outputting raw hidden-states without any specific head on top.",
DISTILBERT_START_DOCSTRING,
DISTILBERT_INPUTS_DOCSTRING,
)
class DistilBertModel(DistilBertPreTrainedModel):
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.
**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 = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertModel.from_pretrained('distilbert-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
"""
def __init__(self, config):
super().__init__(config)
@@ -445,7 +413,34 @@ class DistilBertModel(DistilBertPreTrainedModel):
for layer, heads in heads_to_prune.items():
self.transformer.layer[layer].attention.prune_heads(heads)
@add_start_docstrings_to_callable(DISTILBERT_INPUTS_DOCSTRING)
def forward(self, input_ids=None, attention_mask=None, head_mask=None, inputs_embeds=None):
r"""
Return:
:obj:`Tuple` comprising various elements depending on the configuration (:class:`~transformers.DistilBertConfig`) 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.
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 = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertModel.from_pretrained('distilbert-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:
@@ -491,38 +486,8 @@ class DistilBertModel(DistilBertPreTrainedModel):
@add_start_docstrings(
"""DistilBert Model with a `masked language modeling` head on top. """,
DISTILBERT_START_DOCSTRING,
DISTILBERT_INPUTS_DOCSTRING,
)
class DistilBertForMaskedLM(DistilBertPreTrainedModel):
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]``
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 = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertForMaskedLM.from_pretrained('distilbert-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)
@@ -541,7 +506,42 @@ class DistilBertForMaskedLM(DistilBertPreTrainedModel):
def get_output_embeddings(self):
return self.vocab_projector
@add_start_docstrings_to_callable(DISTILBERT_INPUTS_DOCSTRING)
def forward(self, input_ids=None, attention_mask=None, head_mask=None, inputs_embeds=None, masked_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]``
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,)``:
Masked language modeling 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 = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertForMaskedLM.from_pretrained('distilbert-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]
"""
dlbrt_output = self.distilbert(
input_ids=input_ids, attention_mask=attention_mask, head_mask=head_mask, inputs_embeds=inputs_embeds
)
@@ -565,39 +565,8 @@ class DistilBertForMaskedLM(DistilBertPreTrainedModel):
"""DistilBert Model transformer with a sequence classification/regression head on top (a linear layer on top of
the pooled output) e.g. for GLUE tasks. """,
DISTILBERT_START_DOCSTRING,
DISTILBERT_INPUTS_DOCSTRING,
)
class DistilBertForSequenceClassification(DistilBertPreTrainedModel):
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 = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertForSequenceClassification.from_pretrained('distilbert-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)
@@ -610,7 +579,43 @@ class DistilBertForSequenceClassification(DistilBertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(DISTILBERT_INPUTS_DOCSTRING)
def forward(self, input_ids=None, attention_mask=None, head_mask=None, 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 = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertForSequenceClassification.from_pretrained('distilbert-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]
"""
distilbert_output = self.distilbert(
input_ids=input_ids, attention_mask=attention_mask, head_mask=head_mask, inputs_embeds=inputs_embeds
)
@@ -638,33 +643,58 @@ class DistilBertForSequenceClassification(DistilBertPreTrainedModel):
"""DistilBert Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of
the hidden-states output to compute `span start logits` and `span end logits`). """,
DISTILBERT_START_DOCSTRING,
DISTILBERT_INPUTS_DOCSTRING,
)
class DistilBertForQuestionAnswering(DistilBertPreTrainedModel):
def __init__(self, config):
super().__init__(config)
self.distilbert = DistilBertModel(config)
self.qa_outputs = nn.Linear(config.dim, config.num_labels)
assert config.num_labels == 2
self.dropout = nn.Dropout(config.qa_dropout)
self.init_weights()
@add_start_docstrings_to_callable(DISTILBERT_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
attention_mask=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::
@@ -677,26 +707,6 @@ class DistilBertForQuestionAnswering(DistilBertPreTrainedModel):
loss, start_scores, end_scores = outputs[:3]
"""
def __init__(self, config):
super().__init__(config)
self.distilbert = DistilBertModel(config)
self.qa_outputs = nn.Linear(config.dim, config.num_labels)
assert config.num_labels == 2
self.dropout = nn.Dropout(config.qa_dropout)
self.init_weights()
def forward(
self,
input_ids=None,
attention_mask=None,
head_mask=None,
inputs_embeds=None,
start_positions=None,
end_positions=None,
):
distilbert_output = self.distilbert(
input_ids=input_ids, attention_mask=attention_mask, head_mask=head_mask, inputs_embeds=inputs_embeds
)
@@ -733,37 +743,8 @@ class DistilBertForQuestionAnswering(DistilBertPreTrainedModel):
"""DistilBert 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. """,
DISTILBERT_START_DOCSTRING,
DISTILBERT_INPUTS_DOCSTRING,
)
class DistilBertForTokenClassification(DistilBertPreTrainedModel):
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 = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertForTokenClassification.from_pretrained('distilbert-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]
"""
def __init__(self, config):
super().__init__(config)
@@ -775,7 +756,41 @@ class DistilBertForTokenClassification(DistilBertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(DISTILBERT_INPUTS_DOCSTRING)
def forward(self, input_ids=None, attention_mask=None, head_mask=None, 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 = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertForTokenClassification.from_pretrained('distilbert-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]
"""
outputs = self.distilbert(
input_ids, attention_mask=attention_mask, head_mask=head_mask, inputs_embeds=inputs_embeds