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

Pytorch RoBERTa

Browse Source
This commit is contained in:
Lysandre
2020-01-20 13:24:04 -05:00
committed by Lysandre Debut
parent f44ff574d3
commit 3e1bc27e1b
3 changed files with 234 additions and 280 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
docs/source/model_doc/roberta.rst
View File

@@ -1,35 +1,45 @@
RoBERTa
----------------------------------------------------
``RobertaConfig``
The RoBERTa model was proposed in `RoBERTa: A Robustly Optimized BERT Pretraining Approach`_
by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer,
Veselin Stoyanov. It is based on Google's BERT model released in 2018.
It builds on BERT and modifies key hyperparameters, removing the next-sentence pretraining
objective and training with much larger mini-batches and learning rates.
This implementation is the same as BertModel with a tiny embeddings tweak as well as a setup for Roberta pretrained
models.
RobertaConfig
~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.RobertaConfig
:members:
``RobertaTokenizer``
RobertaTokenizer
~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.RobertaTokenizer
:members:
``RobertaModel``
RobertaModel
~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.RobertaModel
:members:
``RobertaForMaskedLM``
RobertaForMaskedLM
~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.RobertaForMaskedLM
:members:
``RobertaForSequenceClassification``
RobertaForSequenceClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.RobertaForSequenceClassification
@@ -42,21 +52,21 @@ RobertaForTokenClassification
.. autoclass:: transformers.RobertaForTokenClassification
:members:
``TFRobertaModel``
TFRobertaModel
~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFRobertaModel
:members:
``TFRobertaForMaskedLM``
TFRobertaForMaskedLM
~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFRobertaForMaskedLM
:members:
``TFRobertaForSequenceClassification``
TFRobertaForSequenceClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFRobertaForSequenceClassification

2
src/transformers/modeling_bert.py
View File

@@ -592,7 +592,7 @@ BERT_INPUTS_DOCSTRING = r"""
Mask to nullify selected heads of the self-attention modules.
Mask values selected in ``[0, 1]``:
: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`):
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.

482
src/transformers/modeling_roberta.py
View File

@@ -23,7 +23,7 @@ import torch.nn as nn
from torch.nn import CrossEntropyLoss, MSELoss
from .configuration_roberta import RobertaConfig
from .file_utils import add_start_docstrings
from .file_utils import add_start_docstrings, add_start_docstrings_to_callable
from .modeling_bert import BertEmbeddings, BertLayerNorm, BertModel, BertPreTrainedModel, gelu
@@ -92,26 +92,11 @@ class RobertaEmbeddings(BertEmbeddings):
return position_ids.unsqueeze(0).expand(input_shape)
ROBERTA_START_DOCSTRING = r""" The RoBERTa model was proposed in
`RoBERTa: A Robustly Optimized BERT Pretraining Approach`_
by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer,
Veselin Stoyanov. It is based on Google's BERT model released in 2018.
ROBERTA_START_DOCSTRING = r"""
It builds on BERT and modifies key hyperparameters, removing the next-sentence pretraining
objective and training with much larger mini-batches and learning rates.
This implementation is the same as BertModel with a tiny embeddings tweak as well as a setup for Roberta pretrained
models.
This model is a PyTorch `torch.nn.Module`_ sub-class. Use it as a regular PyTorch Module and
This model is a PyTorch `torch.nn.Module <https://pytorch.org/docs/stable/nn.html#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.
.. _`RoBERTa: A Robustly Optimized BERT Pretraining Approach`:
https://arxiv.org/abs/1907.11692
.. _`torch.nn.Module`:
https://pytorch.org/docs/stable/nn.html#module
Parameters:
config (:class:`~transformers.RobertaConfig`): 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.
@@ -119,47 +104,38 @@ ROBERTA_START_DOCSTRING = r""" The RoBERTa model was proposed in
"""
ROBERTA_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, RoBERTa input sequence should be formatted with <s> and </s> tokens as follows:
(a) For sequence pairs:
``tokens: <s> Is this Jacksonville ? </s> </s> No it is not . </s>``
(b) For single sequences:
``tokens: <s> the dog is hairy . </s>``
Fully encoded sequences or sequence pairs can be obtained using the RobertaTokenizer.encode function with
the ``add_special_tokens`` parameter set to ``True``.
RoBERTa 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.RobertaTokenizer`.
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` need to be trained) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
Optional segment token indices to indicate first and second portions of the inputs.
This embedding matrice is not trained (not pretrained during RoBERTa pretraining), you will have to train it
during finetuning.
`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)``:
Selected in the range ``[0, config.max_position_embeddings - 1]``.
`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**.
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.
"""
@@ -168,36 +144,11 @@ ROBERTA_INPUTS_DOCSTRING = r"""
@add_start_docstrings(
"The bare RoBERTa Model transformer outputting raw hidden-states without any specific head on top.",
ROBERTA_START_DOCSTRING,
ROBERTA_INPUTS_DOCSTRING,
)
class RobertaModel(BertModel):
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::
tokenizer = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaModel.from_pretrained('roberta-base')
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
"""
This class overrides :class:`~transformers.BertModel`. Please check the
superclass for the appropriate documentation alongside usage examples.
"""
config_class = RobertaConfig
pretrained_model_archive_map = ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP
@@ -217,38 +168,9 @@ class RobertaModel(BertModel):
@add_start_docstrings(
"""RoBERTa Model with a `language modeling` head on top. """, ROBERTA_START_DOCSTRING, ROBERTA_INPUTS_DOCSTRING
"""RoBERTa Model with a `language modeling` head on top. """, ROBERTA_START_DOCSTRING
)
class RobertaForMaskedLM(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]``
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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForMaskedLM.from_pretrained('roberta-base')
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]
"""
config_class = RobertaConfig
pretrained_model_archive_map = ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP
base_model_prefix = "roberta"
@@ -264,6 +186,7 @@ class RobertaForMaskedLM(BertPreTrainedModel):
def get_output_embeddings(self):
return self.lm_head.decoder
@add_start_docstrings_to_callable(ROBERTA_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
@@ -274,6 +197,40 @@ class RobertaForMaskedLM(BertPreTrainedModel):
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.RobertaConfig`) and inputs:
masked_lm_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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForMaskedLM.from_pretrained('roberta-base')
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.roberta(
input_ids,
attention_mask=attention_mask,
@@ -324,39 +281,8 @@ class RobertaLMHead(nn.Module):
"""RoBERTa Model transformer with a sequence classification/regression head on top (a linear layer
on top of the pooled output) e.g. for GLUE tasks. """,
ROBERTA_START_DOCSTRING,
ROBERTA_INPUTS_DOCSTRING,
)
class RobertaForSequenceClassification(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]``.
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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForSequenceClassification.from_pretrained('roberta-base')
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]
"""
config_class = RobertaConfig
pretrained_model_archive_map = ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP
base_model_prefix = "roberta"
@@ -368,6 +294,7 @@ class RobertaForSequenceClassification(BertPreTrainedModel):
self.roberta = RobertaModel(config)
self.classifier = RobertaClassificationHead(config)
@add_start_docstrings_to_callable(ROBERTA_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
@@ -378,6 +305,41 @@ class RobertaForSequenceClassification(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.RobertaConfig`) 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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForSequenceClassification.from_pretrained('roberta-base')
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.roberta(
input_ids,
attention_mask=attention_mask,
@@ -407,78 +369,8 @@ class RobertaForSequenceClassification(BertPreTrainedModel):
"""Roberta 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. """,
ROBERTA_START_DOCSTRING,
ROBERTA_INPUTS_DOCSTRING,
)
class RobertaForMultipleChoice(BertPreTrainedModel):
r"""
Inputs:
**input_ids**: ``torch.LongTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Indices of input sequence tokens in the vocabulary.
The second dimension of the input (`num_choices`) indicates the number of choices to score.
To match pre-training, RoBerta input sequence should be formatted with [CLS] and [SEP] tokens as follows:
(a) For sequence pairs:
``tokens: [CLS] is this jack ##son ##ville ? [SEP] [SEP] no it is not . [SEP]``
``token_type_ids: 0 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``
Indices can be obtained using :class:`transformers.BertTokenizer`.
See :func:`transformers.PreTrainedTokenizer.encode` and
:func:`transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
**token_type_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Segment token indices to indicate first and second portions of the inputs.
The second dimension of the input (`num_choices`) indicates the number of choices to score.
Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1``
**attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
Mask to avoid performing attention on padding token indices.
The second dimension of the input (`num_choices`) indicates the number of choices to score.
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)``:
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.
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.
**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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForMultipleChoice.from_pretrained('roberta-base')
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]
"""
config_class = RobertaConfig
pretrained_model_archive_map = ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP
base_model_prefix = "roberta"
@@ -492,6 +384,7 @@ class RobertaForMultipleChoice(BertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(ROBERTA_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
@@ -502,6 +395,43 @@ class RobertaForMultipleChoice(BertPreTrainedModel):
head_mask=None,
inputs_embeds=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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForMultipleChoice.from_pretrained('roberta-base')
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]
flat_input_ids = input_ids.view(-1, input_ids.size(-1))
@@ -535,37 +465,8 @@ class RobertaForMultipleChoice(BertPreTrainedModel):
"""Roberta 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. """,
ROBERTA_START_DOCSTRING,
ROBERTA_INPUTS_DOCSTRING,
)
class RobertaForTokenClassification(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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForTokenClassification.from_pretrained('roberta-base')
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]
"""
config_class = RobertaConfig
pretrained_model_archive_map = ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP
base_model_prefix = "roberta"
@@ -580,6 +481,7 @@ class RobertaForTokenClassification(BertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(ROBERTA_INPUTS_DOCSTRING)
def forward(
self,
input_ids=None,
@@ -590,6 +492,39 @@ class RobertaForTokenClassification(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.RobertaConfig`) 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 = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaForTokenClassification.from_pretrained('roberta-base')
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.roberta(
input_ids,
@@ -644,41 +579,8 @@ class RobertaClassificationHead(nn.Module):
"""Roberta 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`). """,
ROBERTA_START_DOCSTRING,
ROBERTA_INPUTS_DOCSTRING,
)
class RobertaForQuestionAnswering(BertPreTrainedModel):
r"""
**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 = RobertaTokenizer.from_pretrained('roberta-large')
model = RobertaForQuestionAnswering.from_pretrained('roberta-large')
question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
input_ids = tokenizer.encode(question, text)
start_scores, end_scores = model(torch.tensor([input_ids]))
all_tokens = tokenizer.convert_ids_to_tokens(input_ids)
answer = ' '.join(all_tokens[torch.argmax(start_scores) : torch.argmax(end_scores)+1])
"""
config_class = RobertaConfig
pretrained_model_archive_map = ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP
base_model_prefix = "roberta"
@@ -692,6 +594,7 @@ class RobertaForQuestionAnswering(BertPreTrainedModel):
self.init_weights()
@add_start_docstrings_to_callable(ROBERTA_INPUTS_DOCSTRING)
def forward(
self,
input_ids,
@@ -699,9 +602,49 @@ class RobertaForQuestionAnswering(BertPreTrainedModel):
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
start_positions=None,
end_positions=None,
):
r"""
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 (: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.
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 (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length,)`):
Span-start scores (before SoftMax).
end_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length,)`):
Span-end 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 = RobertaTokenizer.from_pretrained('roberta-large')
model = RobertaForQuestionAnswering.from_pretrained('roberta-large')
question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
input_ids = tokenizer.encode(question, text)
start_scores, end_scores = model(torch.tensor([input_ids]))
all_tokens = tokenizer.convert_ids_to_tokens(input_ids)
answer = ' '.join(all_tokens[torch.argmax(start_scores) : torch.argmax(end_scores)+1])
"""
outputs = self.roberta(
input_ids,
@@ -709,6 +652,7 @@ class RobertaForQuestionAnswering(BertPreTrainedModel):
token_type_ids=token_type_ids,
position_ids=position_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds
)
sequence_output = outputs[0]