From 44a5b4bbe7864ced756f6aac7f6383438923082b Mon Sep 17 00:00:00 2001 From: Lysandre Date: Wed, 29 Jan 2020 11:45:38 -0500 Subject: [PATCH] Update documentation --- docs/source/model_doc/xlmroberta.rst | 27 +++ src/transformers/modeling_tf_xlm_roberta.py | 218 +++----------------- 2 files changed, 54 insertions(+), 191 deletions(-) diff --git a/docs/source/model_doc/xlmroberta.rst b/docs/source/model_doc/xlmroberta.rst index 66ea48858a..8ddb38b1c2 100644 --- a/docs/source/model_doc/xlmroberta.rst +++ b/docs/source/model_doc/xlmroberta.rst @@ -73,3 +73,30 @@ XLMRobertaForTokenClassification .. autoclass:: transformers.XLMRobertaForTokenClassification :members: + +TFXLMRobertaModel +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.TFXLMRobertaModel + :members: + + +TFXLMRobertaForMaskedLM +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.TFXLMRobertaForMaskedLM + :members: + + +TFXLMRobertaForSequenceClassification +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.TFXLMRobertaForSequenceClassification + :members: + + +TFXLMRobertaForTokenClassification +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. autoclass:: transformers.TFXLMRobertaForTokenClassification + :members: diff --git a/src/transformers/modeling_tf_xlm_roberta.py b/src/transformers/modeling_tf_xlm_roberta.py index 20b1394552..defed5cd12 100644 --- a/src/transformers/modeling_tf_xlm_roberta.py +++ b/src/transformers/modeling_tf_xlm_roberta.py @@ -33,22 +33,26 @@ logger = logging.getLogger(__name__) TF_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. +XLM_ROBERTA_START_DOCSTRING = r""" - It is a large multi-lingual language model, trained on 2.5TB of filtered CommonCrawl data. + .. note:: - This implementation is the same as RoBERTa. + TF 2.0 models accepts two formats as inputs: - This model is a tf.keras.Model `tf.keras.Model`_ sub-class. Use it as a regular TF 2.0 Keras Model and - refer to the TF 2.0 documentation for all matter related to general usage and behavior. + - having all inputs as keyword arguments (like PyTorch models), or + - having all inputs as a list, tuple or dict in the first positional arguments. - .. _`Unsupervised Cross-lingual Representation Learning at Scale`: - https://arxiv.org/abs/1911.02116 + This second option is useful when using :obj:`tf.keras.Model.fit()` method which currently requires having + all the tensors in the first argument of the model call function: :obj:`model(inputs)`. - .. _`tf.keras.Model`: - https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/Model + If you choose this second option, there are three possibilities you can use to gather all the input Tensors + in the first positional argument : + + - a single Tensor with input_ids only and nothing else: :obj:`model(inputs_ids)` + - a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: + :obj:`model([input_ids, attention_mask])` or :obj:`model([input_ids, attention_mask, token_type_ids])` + - a dictionary with one or several input Tensors associated to the input names given in the docstring: + :obj:`model({'input_ids': input_ids, 'token_type_ids': token_type_ids})` Parameters: config (:class:`~transformers.XLMRobertaConfig`): Model configuration class with all the parameters of the @@ -56,100 +60,14 @@ XLM_ROBERTA_START_DOCSTRING = r""" The XLM-RoBERTa model was proposed in Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights. """ -XLM_ROBERTA_INPUTS_DOCSTRING = r""" - Inputs: - **input_ids**: ``Numpy array`` or ``tf.Tensor`` 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`) ``Numpy array`` or ``tf.Tensor`` 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) ``Numpy array`` or ``tf.Tensor`` 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`) ``Numpy array`` or ``tf.Tensor`` 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`) ``Numpy array`` or ``tf.Tensor`` 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`) ``Numpy array`` or ``tf.Tensor`` 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 TFXLMRobertaModel(TFRobertaModel): - r""" - Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs: - **last_hidden_state**: ``Numpy array`` or ``tf.Tensor`` of shape ``(batch_size, sequence_length, hidden_size)`` - Sequence of hidden-states at the output of the last layer of the model. - **pooler_output**: ``Numpy array`` or ``tf.Tensor`` 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 ``Numpy array`` or ``tf.Tensor`` (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 ``Numpy array`` or ``tf.Tensor`` (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 = TFXLMRobertaModel.from_pretrained('xlm-roberta-large') - input_ids = tf.constant(tokenizer.encode("Schloß Nymphenburg ist sehr schön ."))[None, :] # 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.TFRobertaModel`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = TF_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP @@ -158,37 +76,11 @@ class TFXLMRobertaModel(TFRobertaModel): @add_start_docstrings( """XLM-RoBERTa Model with a `language modeling` head on top. """, XLM_ROBERTA_START_DOCSTRING, - XLM_ROBERTA_INPUTS_DOCSTRING, ) class TFXLMRobertaForMaskedLM(TFRobertaForMaskedLM): - r""" - **masked_lm_labels**: (`optional`) ``Numpy array`` or ``tf.Tensor`` 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) ``Numpy array`` or ``tf.Tensor`` of shape ``(1,)``: - Masked language modeling loss. - **prediction_scores**: ``Numpy array`` or ``tf.Tensor`` 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 ``Numpy array`` or ``tf.Tensor`` (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 ``Numpy array`` or ``tf.Tensor`` (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 = TFXLMRobertaForMaskedLM.from_pretrained('xlm-roberta-large') - input_ids = tf.constant(tokenizer.encode("Schloß Nymphenburg ist sehr schön ."))[None, :] # Batch size 1 - outputs = model(input_ids) - loss, prediction_scores = outputs[:2] - + """ + This class overrides :class:`~transformers.TFRobertaForMaskedLM`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = TF_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP @@ -198,81 +90,25 @@ class TFXLMRobertaForMaskedLM(TFRobertaForMaskedLM): """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 TFXLMRobertaForSequenceClassification(TFRobertaForSequenceClassification): - r""" - **labels**: (`optional`) ``Numpy array`` or ``tf.Tensor`` 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) ``Numpy array`` or ``tf.Tensor`` of shape ``(1,)``: - Classification (or regression if config.num_labels==1) loss. - **logits**: ``Numpy array`` or ``tf.Tensor`` 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 ``Numpy array`` or ``tf.Tensor`` (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 ``Numpy array`` or ``tf.Tensor`` (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 = TFXLMRobertaForSequenceClassification.from_pretrained('xlm-roberta-large') - input_ids = tf.constant(tokenizer.encode("Schloß Nymphenburg ist sehr schön ."))[None, :] # Batch size 1 - outputs = model(input_ids) - loss, logits = outputs[:2] - + """ + This class overrides :class:`~transformers.TFRobertaForSequenceClassification`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = TF_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP -@add_start_docstrings( - """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, -) @add_start_docstrings( """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 TFXLMRobertaForTokenClassification(TFRobertaForTokenClassification): - r""" - **labels**: (`optional`) ``Numpy array`` or ``tf.Tensor`` 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) ``Numpy array`` or ``tf.Tensor`` of shape ``(1,)``: - Classification loss. - **scores**: ``Numpy array`` or ``tf.Tensor`` 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 ``Numpy array`` or ``tf.Tensor`` (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 ``Numpy array`` or ``tf.Tensor`` (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 = TFXLMRobertaForTokenClassification.from_pretrained('xlm-roberta-large') - input_ids = tf.constant(tokenizer.encode("Schloß Nymphenburg ist sehr schön .", add_special_tokens=True))[None, :] # Batch size 1 - outputs = model(input_ids) - loss, scores = outputs[:2] - + """ + This class overrides :class:`~transformers.TFRobertaForTokenClassification`. Please check the + superclass for the appropriate documentation alongside usage examples. """ config_class = XLMRobertaConfig pretrained_model_archive_map = TF_XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP