diff --git a/docs/source/index.rst b/docs/source/index.rst index bfef01d00a..988d530134 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -97,3 +97,4 @@ The library currently contains PyTorch and Tensorflow implementations, pre-train model_doc/ctrl model_doc/camembert model_doc/albert + model_doc/xlmroberta \ No newline at end of file diff --git a/docs/source/model_doc/xlmroberta.rst b/docs/source/model_doc/xlmroberta.rst new file mode 100644 index 0000000000..8944c53895 --- /dev/null +++ b/docs/source/model_doc/xlmroberta.rst @@ -0,0 +1,68 @@ +XLM-RoBERTa +------------------------------------------ + +The XLM-RoBERTa model was proposed in `Unsupervised Cross-lingual Representation Learning at Scale`_ +by Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer and Veselin Stoyanov. It is based on Facebook's RoBERTa model released in 2019. + +It is a large multi-lingual language model, trained on 2.5TB of filtered CommonCrawl data. + +This implementation is the same as RoBERTa. + +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. + +.. _`Unsupervised Cross-lingual Representation Learning at Scale`: + https://arxiv.org/abs/1911.02116 + +.. _`torch.nn.Module`: + https://pytorch.org/docs/stable/nn.html#module + + +XLMRobertaConfig +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.XLMRobertaConfig + :members: + + +XLMRobertaTokenizer +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.XLMRobertaTokenizer + :members: + + +XLMRobertaModel +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.XLMRobertaModel + :members: + + +XLMRobertaForMaskedLM +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.XLMRobertaForMaskedLM + :members: + + +XLMRobertaForSequenceClassification +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.XLMRobertaForSequenceClassification + :members: + + +XLMRobertaForMultipleChoice +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.XLMRobertaForMultipleChoice + :members: + + +XLMRobertaForTokenClassification +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.XLMRobertaForTokenClassification + :members: + diff --git a/src/transformers/configuration_xlm_roberta.py b/src/transformers/configuration_xlm_roberta.py index 0208a0449c..7fe4b642d7 100644 --- a/src/transformers/configuration_xlm_roberta.py +++ b/src/transformers/configuration_xlm_roberta.py @@ -34,5 +34,9 @@ XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = { class XLMRobertaConfig(RobertaConfig): + """ + This class overrides :class:`~transformers.RobertaConfig`. Please check the + superclass for the appropriate documentation alongside usage examples. + """ pretrained_config_archive_map = XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP model_type = "xlm-roberta" diff --git a/src/transformers/modeling_bert.py b/src/transformers/modeling_bert.py index 67a86ef70b..f9848b9411 100644 --- a/src/transformers/modeling_bert.py +++ b/src/transformers/modeling_bert.py @@ -549,12 +549,6 @@ 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. - .. _`BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding`: - https://arxiv.org/abs/1810.04805 - - .. _`torch.nn.Module`: - https://pytorch.org/docs/stable/nn.html#module - Parameters: config (:class:`~transformers.BertConfig`): Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. diff --git a/src/transformers/modeling_xlm_roberta.py b/src/transformers/modeling_xlm_roberta.py index f7ab857e63..e9aa35ad01 100644 --- a/src/transformers/modeling_xlm_roberta.py +++ b/src/transformers/modeling_xlm_roberta.py @@ -41,123 +41,25 @@ XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP = { } -XLM_ROBERTA_START_DOCSTRING = r""" The XLM-RoBERTa model was proposed in - `Unsupervised Cross-lingual Representation Learning at Scale`_ - by Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer and Veselin Stoyanov. It is based on Facebook's RoBERTa model released in 2019. - - It is a large multi-lingual language model, trained on 2.5TB of filtered CommonCrawl data. - - This implementation is the same as RoBERTa. - +XLM_ROBERTA_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. - .. _`Unsupervised Cross-lingual Representation Learning at Scale`: - https://arxiv.org/abs/1911.02116 - - .. _`torch.nn.Module`: - https://pytorch.org/docs/stable/nn.html#module - Parameters: config (:class:`~transformers.XLMRobertaConfig`): Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights. """ -XLM_ROBERTA_INPUTS_DOCSTRING = r""" - Inputs: - **input_ids**: ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``: - Indices of input sequence tokens in the vocabulary. - To match pre-training, XLM-RoBERTa input sequence should be formatted with and tokens as follows: - - (a) For sequence pairs: - - ``tokens: Is this Jacksonville ? No it is not . `` - - (b) For single sequences: - - ``tokens: the dog is hairy . `` - - Fully encoded sequences or sequence pairs can be obtained using the XLMRobertaTokenizer.encode function with - the ``add_special_tokens`` parameter set to ``True``. - - XLM-RoBERTa is a model with absolute position embeddings so it's usually advised to pad the inputs on - the right rather than the left. - - 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)``: - 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 XLM-RoBERTa pretraining), you will have to train it - during finetuning. - Indices are selected in ``[0, 1]``: ``0`` corresponds to a `sentence A` token, ``1`` - corresponds to a `sentence B` token - (see `BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding`_ for more details). - **position_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``: - Indices of positions of each input sequence tokens in the position embeddings. - Selected in the range ``[0, config.max_position_embeddings - 1[``. - **head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``: - Mask to nullify selected heads of the self-attention modules. - Mask values selected in ``[0, 1]``: - ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**. - **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. -""" - @add_start_docstrings( "The bare XLM-RoBERTa Model transformer outputting raw hidden-states without any specific head on top.", XLM_ROBERTA_START_DOCSTRING, - XLM_ROBERTA_INPUTS_DOCSTRING, ) class XLMRobertaModel(RobertaModel): - 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) - eo match pre-training, XLM-RoBERTa input sequence should be formatted with and tokens as follows: - - (a) For sequence pairs: - - ``tokens: is this jack ##son ##ville ? no it is not . `` - - ``token_type_ids: 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1`` - - (b) For single sequences: - - ``tokens: the dog is hairy . `` - - ``token_type_ids: 0 0 0 0 0 0 0`` - - 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 = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large') - model = XLMRobertaModel.from_pretrained('xlm-roberta-large') - input_ids = torch.tensor(tokenizer.encode("Schloß Nymphenburg ist sehr schön .")).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.RobertaModel`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP @@ -166,37 +68,11 @@ class XLMRobertaModel(RobertaModel): @add_start_docstrings( """XLM-RoBERTa Model with a `language modeling` head on top. """, XLM_ROBERTA_START_DOCSTRING, - XLM_ROBERTA_INPUTS_DOCSTRING, ) class XLMRobertaForMaskedLM(RobertaForMaskedLM): - 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 ``[-1, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring) - Tokens with indices set to ``-1`` are ignored (masked), the loss is only computed for the tokens with labels - in ``[0, ..., config.vocab_size]`` - - Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs: - **loss**: (`optional`, returned when ``masked_lm_labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``: - Masked language modeling loss. - **prediction_scores**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, config.vocab_size)`` - Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). - **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``) - list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings) - of shape ``(batch_size, sequence_length, hidden_size)``: - Hidden-states of the model at the output of each layer plus the initial embedding outputs. - **attentions**: (`optional`, returned when ``config.output_attentions=True``) - list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``: - Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - - Examples:: - - tokenizer = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large') - model = XLMRobertaForMaskedLM.from_pretrained('xlm-roberta-large') - input_ids = torch.tensor(tokenizer.encode("Schloß Nymphenburg ist sehr schön .")).unsqueeze(0) # Batch size 1 - outputs = model(input_ids, masked_lm_labels=input_ids) - loss, prediction_scores = outputs[:2] - + """ + This class overrides :class:`~transformers.RobertaForMaskedLM`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP @@ -206,38 +82,11 @@ class XLMRobertaForMaskedLM(RobertaForMaskedLM): """XLM-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. """, XLM_ROBERTA_START_DOCSTRING, - XLM_ROBERTA_INPUTS_DOCSTRING, ) class XLMRobertaForSequenceClassification(RobertaForSequenceClassification): - 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 = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large') - model = XLMRobertaForSequenceClassification.from_pretrained('xlm-roberta-large') - input_ids = torch.tensor(tokenizer.encode("Schloß Nymphenburg ist sehr schön .")).unsqueeze(0) # Batch size 1 - labels = torch.tensor([1]).unsqueeze(0) # Batch size 1 - outputs = model(input_ids, labels=labels) - loss, logits = outputs[:2] - + """ + This class overrides :class:`~transformers.RobertaForSequenceClassification`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP @@ -247,34 +96,11 @@ class XLMRobertaForSequenceClassification(RobertaForSequenceClassification): """XLM-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. """, XLM_ROBERTA_START_DOCSTRING, - XLM_ROBERTA_INPUTS_DOCSTRING, ) class XLMRobertaForMultipleChoice(RobertaForMultipleChoice): - r""" - 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 = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large') - model = XLMRobertaForMultipleChoice.from_pretrained('xlm-roberta-large') - choices = ["Schloß Nymphenburg ist sehr schön .", "Der Schloßkanal auch !"] - 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] - + """ + This class overrides :class:`~transformers.RobertaForMultipleChoice`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP @@ -284,36 +110,11 @@ class XLMRobertaForMultipleChoice(RobertaForMultipleChoice): """XLM-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. """, XLM_ROBERTA_START_DOCSTRING, - XLM_ROBERTA_INPUTS_DOCSTRING, ) class XLMRobertaForTokenClassification(RobertaForTokenClassification): - 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 = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large') - model = XLMRobertaForTokenClassification.from_pretrained('xlm-roberta-large') - input_ids = torch.tensor(tokenizer.encode("Schloß Nymphenburg ist sehr schön .", 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] - + """ + This class overrides :class:`~transformers.RobertaForTokenClassification`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP