Fix TF input docstrings to refer to tf.Tensor rather than torch.FloatTensor. (#4051)

README.md

@@ -63,7 +63,7 @@ Choose the right framework for every part of a model's lifetime
 
 ## Installation
 
-This repo is tested on Python 3.6+, PyTorch 1.0.0+ and TensorFlow 2.0.0-rc1
+This repo is tested on Python 3.6+, PyTorch 1.0.0+ and TensorFlow 2.0.
 
 You should install 🤗 Transformers in a [virtual environment](https://docs.python.org/3/library/venv.html). If you're unfamiliar with Python virtual environments, check out the [user guide](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/).
 

src/transformers/modeling_tf_albert.py

@@ -846,7 +846,7 @@ class TFAlbertForQuestionAnswering(TFAlbertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.AlbertConfig`) and inputs:
         start_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length,)`):
             Span-start scores (before SoftMax).
         end_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length,)`):

src/transformers/modeling_tf_bert.py

@@ -673,7 +673,7 @@ class TFBertModel(TFBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
         last_hidden_state (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the model.
         pooler_output (:obj:`tf.Tensor` of shape :obj:`(batch_size, hidden_size)`):
@@ -730,7 +730,7 @@ class TFBertForPreTraining(TFBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
         prediction_scores (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`):
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         seq_relationship_scores (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, 2)`):
@@ -786,7 +786,7 @@ class TFBertForMaskedLM(TFBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
         prediction_scores (:obj:`Numpy array` or :obj:`tf.Tensor` 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(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -836,7 +836,7 @@ class TFBertForNextSentencePrediction(TFBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
         seq_relationship_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, 2)`)
             Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -892,7 +892,7 @@ class TFBertForSequenceClassification(TFBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
         logits (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, config.num_labels)`):
             Classification (or regression if config.num_labels==1) scores (before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -967,7 +967,7 @@ class TFBertForMultipleChoice(TFBertPreTrainedModel):
     ):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
         classification_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, num_choices)`:
             `num_choices` is the size of the second dimension of the input tensors. (see `input_ids` above).
 
@@ -1069,7 +1069,7 @@ class TFBertForTokenClassification(TFBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
         scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.num_labels)`):
             Classification scores (before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -1126,7 +1126,7 @@ class TFBertForQuestionAnswering(TFBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
         start_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length,)`):
             Span-start scores (before SoftMax).
         end_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length,)`):

src/transformers/modeling_tf_distilbert.py

@@ -545,7 +545,7 @@ class TFDistilBertModel(TFDistilBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
         last_hidden_state (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the model.
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -619,7 +619,7 @@ class TFDistilBertForMaskedLM(TFDistilBertPreTrainedModel):
         r"""
 
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
         prediction_scores (:obj:`Numpy array` or :obj:`tf.Tensor` 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(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -683,7 +683,7 @@ class TFDistilBertForSequenceClassification(TFDistilBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
         logits (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, config.num_labels)`):
             Classification (or regression if config.num_labels==1) scores (before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -741,7 +741,7 @@ class TFDistilBertForTokenClassification(TFDistilBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
         scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.num_labels)`):
             Classification scores (before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -798,7 +798,7 @@ class TFDistilBertForQuestionAnswering(TFDistilBertPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers,DistilBertConfig`) and inputs:
         start_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length,)`):
             Span-start scores (before SoftMax).
         end_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length,)`):

src/transformers/modeling_tf_electra.py

@@ -357,7 +357,7 @@ class TFElectraModel(TFElectraPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.ElectraConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.ElectraConfig`) and inputs:
         last_hidden_state (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the model.
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -418,7 +418,7 @@ class TFElectraForPreTraining(TFElectraPreTrainedModel):
     ):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.ElectraConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.ElectraConfig`) and inputs:
         scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.num_labels)`):
             Prediction scores of the head (scores for each token before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -511,7 +511,7 @@ class TFElectraForMaskedLM(TFElectraPreTrainedModel):
     ):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.ElectraConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.ElectraConfig`) and inputs:
         prediction_scores (:obj:`Numpy array` or :obj:`tf.Tensor` 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(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -578,7 +578,7 @@ class TFElectraForTokenClassification(TFElectraPreTrainedModel):
     ):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.ElectraConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.ElectraConfig`) and inputs:
         scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.num_labels)`):
             Classification scores (before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):

src/transformers/modeling_tf_roberta.py

@@ -49,8 +49,8 @@ class TFRobertaEmbeddings(TFBertEmbeddings):
         """ Replace non-padding symbols with their position numbers. Position numbers begin at
         padding_idx+1. Padding symbols are ignored. This is modified from fairseq's
         `utils.make_positions`.
-        :param torch.Tensor x:
-        :return torch.Tensor:
+        :param tf.Tensor x:
+        :return tf.Tensor:
         """
         mask = tf.cast(tf.math.not_equal(x, self.padding_idx), dtype=tf.int32)
         incremental_indicies = tf.math.cumsum(mask, axis=1) * mask
@@ -59,8 +59,8 @@ class TFRobertaEmbeddings(TFBertEmbeddings):
     def create_position_ids_from_inputs_embeds(self, inputs_embeds):
         """ We are provided embeddings directly. We cannot infer which are padded so just generate
         sequential position ids.
-        :param torch.Tensor inputs_embeds:
-        :return torch.Tensor:
+        :param tf.Tensor inputs_embeds:
+        :return tf.Tensor:
         """
         seq_length = shape_list(inputs_embeds)[1]
 
@@ -188,7 +188,7 @@ class TFRobertaModel(TFRobertaPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Returns:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
         last_hidden_state (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the model.
         pooler_output (:obj:`tf.Tensor` of shape :obj:`(batch_size, hidden_size)`):
@@ -271,7 +271,7 @@ class TFRobertaForMaskedLM(TFRobertaPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
         prediction_scores (:obj:`Numpy array` or :obj:`tf.Tensor` 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(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -349,7 +349,7 @@ class TFRobertaForSequenceClassification(TFRobertaPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
         logits (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, config.num_labels)`):
             Classification (or regression if config.num_labels==1) scores (before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -406,7 +406,7 @@ class TFRobertaForTokenClassification(TFRobertaPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
         scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.num_labels)`):
             Classification scores (before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when :obj:`config.output_hidden_states=True`):
@@ -462,7 +462,7 @@ class TFRobertaForQuestionAnswering(TFRobertaPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.RobertaConfig`) and inputs:
         start_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length,)`):
             Span-start scores (before SoftMax).
         end_scores (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length,)`):

src/transformers/modeling_tf_t5.py

@@ -797,7 +797,7 @@ T5_INPUTS_DOCSTRING = r"""
             Used in the cross-attention of the decoder.
         decoder_attention_mask (:obj:`tf.Tensor` of shape :obj:`(batch_size, tgt_seq_len)`, `optional`, defaults to :obj:`None`):
             Default behavior: generate a tensor that ignores pad tokens in decoder_input_ids. Causal mask will also be used by default.
-        decoder_past_key_value_states (:obj:`tuple(tuple(torch.FloatTensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
+        decoder_past_key_value_states (:obj:`tuple(tuple(tf.Tensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
             Contains pre-computed key and value hidden-states of the attention blocks.
             Can be used to speed up decoding.
             If `decoder_past_key_value_states` are used, the user can optionally input only the last `decoder_input_ids`
@@ -863,7 +863,7 @@ class TFT5Model(TFT5PreTrainedModel):
         last_hidden_state (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the model.
             If `decoder_past_key_value_states` is used only the last hidden-state of the sequences of shape :obj:`(batch_size, 1, hidden_size)` is output.
-        decoder_past_key_value_states (:obj:`tuple(tuple(torch.FloatTensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length, embed_size_per_head)`, `optional`, returned when ``use_cache=True``):
+        decoder_past_key_value_states (:obj:`tuple(tuple(tf.Tensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length, embed_size_per_head)`, `optional`, returned when ``use_cache=True``):
             Contains pre-computed key and value hidden-states of the attention blocks.
             Can be used to speed up sequential decoding (see `decoder_past_key_value_states` input).
             Note that when using `decoder_past_key_value_states`, the model only outputs the last `hidden-state` of the sequence of shape :obj:`(batch_size, 1, config.vocab_size)`.
@@ -985,7 +985,7 @@ class TFT5ForConditionalGeneration(TFT5PreTrainedModel):
             Classification loss (cross entropy).
         prediction_scores (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`)
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
-        decoder_past_key_value_states (:obj:`tuple(tuple(torch.FloatTensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length, embed_size_per_head)`, `optional`, returned when ``use_cache=True``):
+        decoder_past_key_value_states (:obj:`tuple(tuple(tf.Tensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length, embed_size_per_head)`, `optional`, returned when ``use_cache=True``):
             Contains pre-computed key and value hidden-states of the attention blocks.
             Can be used to speed up sequential decoding (see `decoder_past_key_value_states` input).
             Note that when using `decoder_past_key_value_states`, the model only outputs the last `prediction_score` of the sequence of shape :obj:`(batch_size, 1, config.vocab_size)`.

src/transformers/modeling_tf_transfo_xl.py

@@ -671,7 +671,7 @@ TRANSFO_XL_INPUTS_DOCSTRING = r"""
             :func:`transformers.PreTrainedTokenizer.encode_plus` for details.
 
             `What are input IDs? <../glossary.html#input-ids>`__
-        mems (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers`):
+        mems (:obj:`List[tf.Tensor]` of length :obj:`config.n_layers`):
             Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model
             (see `mems` output below). Can be used to speed up sequential decoding. The token ids which have their mems
             given to this model should not be passed as input ids as they have already been computed.
@@ -699,20 +699,20 @@ class TFTransfoXLModel(TFTransfoXLPreTrainedModel):
     def call(self, inputs, **kwargs):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.TransfoXLConfig`) and inputs:
-        last_hidden_state (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.TransfoXLConfig`) and inputs:
+        last_hidden_state (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the last layer of the model.
-        mems (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers`):
+        mems (:obj:`List[tf.Tensor]` of length :obj:`config.n_layers`):
             Contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `mems` input) to speed up sequential decoding. The token ids which have their past given to this model
             should not be passed as input ids as they have already been computed.
-        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)
+        hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when ``config.output_hidden_states=True``):
+            Tuple of :obj:`tf.Tensor` (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
+        attentions (:obj:`tuple(tf.Tensor)`, `optional`, returned when ``config.output_attentions=True``):
+            Tuple of :obj:`tf.Tensor` (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
@@ -788,20 +788,20 @@ class TFTransfoXLLMHeadModel(TFTransfoXLPreTrainedModel):
     def call(self, inputs, mems=None, head_mask=None, inputs_embeds=None, labels=None, training=False):
         r"""
     Return:
-        :obj:`tuple(torch.FloatTensor)` comprising various elements depending on the configuration (:class:`~transformers.TransfoXLConfig`) and inputs:
-        prediction_scores (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`):
+        :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.TransfoXLConfig`) and inputs:
+        prediction_scores (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`):
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
-        mems (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers`):
+        mems (:obj:`List[tf.Tensor]` of length :obj:`config.n_layers`):
             Contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `past` input) to speed up sequential decoding. The token ids which have their past given to this model
             should not be passed as input ids as they have already been computed.
-        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)
+        hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when ``config.output_hidden_states=True``):
+            Tuple of :obj:`tf.Tensor` (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
+        attentions (:obj:`tuple(tf.Tensor)`, `optional`, returned when ``config.output_attentions=True``):
+            Tuple of :obj:`tf.Tensor` (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

src/transformers/modeling_tf_utils.py

@@ -491,7 +491,7 @@ class TFPreTrainedModel(tf.keras.Model, TFModelUtilsMixin):
 
             input_ids: (`optional`) `tf.Tensor` of `dtype=tf.int32` of shape `(batch_size, sequence_length)`
                 The sequence used as a prompt for the generation. If `None` the method initializes
-                it as an empty `torch.LongTensor` of shape `(1,)`.
+                it as an empty `tf.Tensor` of shape `(1,)`.
 
             max_length: (`optional`) int
                 The max length of the sequence to be generated.  Between 1 and infinity. Default to 20.