Update documentation

docs/source/model_doc/camembert.rst

@@ -69,3 +69,31 @@ CamembertForTokenClassification
 
 .. autoclass:: transformers.CamembertForTokenClassification
     :members:
+
+
+TFCamembertModel
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.TFCamembertModel
+    :members:
+
+
+TFCamembertForMaskedLM
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.TFCamembertForMaskedLM
+    :members:
+
+
+TFCamembertForSequenceClassification
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.TFCamembertForSequenceClassification
+    :members:
+
+
+TFCamembertForTokenClassification
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.TFCamembertForTokenClassification
+    :members:

src/transformers/convert_pytorch_checkpoint_to_tf2.py

@@ -173,9 +173,6 @@ else:
         None,
         None,
         None,
-        None,
-        None,
-        None,
     )
 
 

src/transformers/modeling_tf_camembert.py

@@ -33,38 +33,26 @@ logger = logging.getLogger(__name__)
 TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP = {}
 
 
-CAMEMBERT_START_DOCSTRING = r"""    The CamemBERT model was proposed in
-    `CamemBERT: a Tasty French Language Model`_
-    by Louis Martin, Benjamin Muller, Pedro Javier Ortiz Suárez, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah, and Benoît Sagot. It is based on Facebook's RoBERTa model released in 2019.
+CAMEMBERT_START_DOCSTRING = r"""
 
-    It is a model trained on 138GB of French text.
+    .. note::
 
-    This implementation is the same as RoBERTa.
-
-    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.
-
-    .. _`CamemBERT: a Tasty French Language Model`:
-        https://arxiv.org/abs/1911.03894
-
-    .. _`tf.keras.Model`:
-        https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/Model
-
-    Note on the model inputs:
         TF 2.0 models accepts two formats as inputs:
 
             - having all inputs as keyword arguments (like PyTorch models), or
             - having all inputs as a list, tuple or dict in the first positional arguments.
 
-        This second option is usefull when using `tf.keras.Model.fit()` method which currently requires having all the tensors in the first argument of the model call function: `model(inputs)`.
+        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)`.
 
-        If you choose this second option, there are three possibilities you can use to gather all the input Tensors in the first positional argument :
+        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: `model(inputs_ids)
+        - 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:
-            `model([input_ids, attention_mask])` or `model([input_ids, attention_mask, token_type_ids])`
-        - a dictionary with one or several input Tensors associaed to the input names given in the docstring:
-            `model({'input_ids': input_ids, 'token_type_ids': token_type_ids})`
+          :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.CamembertConfig`): Model configuration class with all the parameters of the
@@ -72,140 +60,30 @@ CAMEMBERT_START_DOCSTRING = r"""    The CamemBERT model was proposed in
             Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights.
 """
 
-CAMEMBERT_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, CamemBERT 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 CamembertTokenizer.encode function with
-            the ``add_special_tokens`` parameter set to ``True``.
-
-            CamemBERT 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 CamemBERT 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 CamemBERT Model transformer outputting raw hidden-states without any specific head on top.",
     CAMEMBERT_START_DOCSTRING,
-    CAMEMBERT_INPUTS_DOCSTRING,
 )
 class TFCamembertModel(TFRobertaModel):
-    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, CamemBERT 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``
-
-            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 = CamembertTokenizer.from_pretrained('camembert-base')
-        model = TFCamembertModel.from_pretrained('camembert-base')
-        input_ids = tf.constant(tokenizer.encode("J'aime le camembert !"))[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 = CamembertConfig
     pretrained_model_archive_map = TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP
 
 
 @add_start_docstrings(
-    """CamemBERT Model with a `language modeling` head on top. """,
-    CAMEMBERT_START_DOCSTRING,
-    CAMEMBERT_INPUTS_DOCSTRING,
+    """CamemBERT Model with a `language modeling` head on top. """, CAMEMBERT_START_DOCSTRING,
 )
 class TFCamembertForMaskedLM(TFRobertaForMaskedLM):
-    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 ``-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 = CamembertTokenizer.from_pretrained('camembert-base')
-        model = TFCamembertForMaskedLM.from_pretrained('camembert-base')
-        input_ids = tf.constant(tokenizer.encode("J'aime le camembert !"))[None, :]  # Batch size 1
-        outputs = model(input_ids, masked_lm_labels=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 = CamembertConfig
     pretrained_model_archive_map = TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP
 
@@ -214,38 +92,13 @@ class TFCamembertForMaskedLM(TFRobertaForMaskedLM):
     """CamemBERT Model transformer with a sequence classification/regression head on top (a linear layer
     on top of the pooled output) e.g. for GLUE tasks. """,
     CAMEMBERT_START_DOCSTRING,
-    CAMEMBERT_INPUTS_DOCSTRING,
 )
 class TFCamembertForSequenceClassification(TFRobertaForSequenceClassification):
-    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 = CamembertTokenizer.from_pretrained('camembert-base')
-        model = TFCamembertForSequenceClassification.from_pretrained('camembert-base')
-        input_ids = tf.constant(tokenizer.encode("J'aime le camembert !"))[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 = CamembertConfig
     pretrained_model_archive_map = TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP
 
@@ -254,35 +107,12 @@ class TFCamembertForSequenceClassification(TFRobertaForSequenceClassification):
     """CamemBERT 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. """,
     CAMEMBERT_START_DOCSTRING,
-    CAMEMBERT_INPUTS_DOCSTRING,
 )
 class TFCamembertForTokenClassification(TFRobertaForTokenClassification):
-    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 = CamembertTokenizer.from_pretrained('camembert-base')
-        model = TFCamembertForTokenClassification.from_pretrained('camembert-base')
-        input_ids = tf.constant(tokenizer.encode("J'aime le camembert !", 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 = CamembertConfig
     pretrained_model_archive_map = TF_CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP