Skip to content

GitLab

Unverified Commit cfd623a8 authored by Sofia Oliveira's avatar Sofia Oliveira Committed by GitHub
Browse files

Add type hints to XLM-Roberta-XL models (#18475) 

* Add type hints to XLM-Roberta-XL models

* Format
parent 17c634fd
Hide whitespace changes
Inline Side-by-side
Showing with 73 additions and 73 deletions
src/transformers/models/xlm_roberta_xl/modeling_xlm_roberta_xl.py
View file @ cfd623a8
...@@ -881,21 +881,21 @@ class XLMRobertaXLForCausalLM(XLMRobertaXLPreTrainedModel): ...@@ -881,21 +881,21 @@ class XLMRobertaXLForCausalLM(XLMRobertaXLPreTrainedModel):
@replace_return_docstrings(output_type=CausalLMOutputWithCrossAttentions, config_class=_CONFIG_FOR_DOC) @replace_return_docstrings(output_type=CausalLMOutputWithCrossAttentions, config_class=_CONFIG_FOR_DOC)
def forward( def forward(
self, self,
input_ids=None, input_ids: Optional[torch.LongTensor] = None,
attention_mask=None, attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids=None, token_type_ids: Optional[torch.LongTensor] = None,
position_ids=None, position_ids: Optional[torch.LongTensor] = None,
head_mask=None, head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds=None, inputs_embeds: Optional[torch.FloatTensor] = None,
encoder_hidden_states=None, encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask=None, encoder_attention_mask: Optional[torch.FloatTensor] = None,
labels=None, labels: Optional[torch.LongTensor] = None,
past_key_values=None, past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
use_cache=None, use_cache: Optional[bool] = None,
output_attentions=None, output_attentions: Optional[bool] = None,
output_hidden_states=None, output_hidden_states: Optional[bool] = None,
return_dict=None, return_dict: Optional[bool] = None,
): ) -> Union[Tuple, CausalLMOutputWithCrossAttentions]:
r""" r"""
encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*): encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
...@@ -1040,19 +1040,19 @@ class XLMRobertaXLForMaskedLM(XLMRobertaXLPreTrainedModel): ...@@ -1040,19 +1040,19 @@ class XLMRobertaXLForMaskedLM(XLMRobertaXLPreTrainedModel):
) )
def forward( def forward(
self, self,
input_ids=None, input_ids: Optional[torch.LongTensor] = None,
attention_mask=None, attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids=None, token_type_ids: Optional[torch.LongTensor] = None,
position_ids=None, position_ids: Optional[torch.LongTensor] = None,
head_mask=None, head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds=None, inputs_embeds: Optional[torch.FloatTensor] = None,
encoder_hidden_states=None, encoder_hidden_states: Optional[torch.Tensor] = None,
encoder_attention_mask=None, encoder_attention_mask: Optional[torch.FloatTensor] = None,
labels=None, labels: Optional[torch.LongTensor] = None,
output_attentions=None, output_attentions: Optional[bool] = None,
output_hidden_states=None, output_hidden_states: Optional[bool] = None,
return_dict=None, return_dict: Optional[bool] = None,
): ) -> Union[Tuple, MaskedLMOutput]:
r""" r"""
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ..., Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
...@@ -1152,17 +1152,17 @@ class XLMRobertaXLForSequenceClassification(XLMRobertaXLPreTrainedModel): ...@@ -1152,17 +1152,17 @@ class XLMRobertaXLForSequenceClassification(XLMRobertaXLPreTrainedModel):
) )
def forward( def forward(
self, self,
input_ids=None, input_ids: Optional[torch.LongTensor] = None,
attention_mask=None, attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids=None, token_type_ids: Optional[torch.LongTensor] = None,
position_ids=None, position_ids: Optional[torch.LongTensor] = None,
head_mask=None, head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds=None, inputs_embeds: Optional[torch.FloatTensor] = None,
labels=None, labels: Optional[torch.LongTensor] = None,
output_attentions=None, output_attentions: Optional[bool] = None,
output_hidden_states=None, output_hidden_states: Optional[bool] = None,
return_dict=None, return_dict: Optional[bool] = None,
): ) -> Union[Tuple, SequenceClassifierOutput]:
r""" r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
...@@ -1250,17 +1250,17 @@ class XLMRobertaXLForMultipleChoice(XLMRobertaXLPreTrainedModel): ...@@ -1250,17 +1250,17 @@ class XLMRobertaXLForMultipleChoice(XLMRobertaXLPreTrainedModel):
) )
def forward( def forward(
self, self,
input_ids=None, input_ids: Optional[torch.LongTensor] = None,
token_type_ids=None, token_type_ids: Optional[torch.LongTensor] = None,
attention_mask=None, attention_mask: Optional[torch.FloatTensor] = None,
labels=None, labels: Optional[torch.LongTensor] = None,
position_ids=None, position_ids: Optional[torch.LongTensor] = None,
head_mask=None, head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds=None, inputs_embeds: Optional[torch.FloatTensor] = None,
output_attentions=None, output_attentions: Optional[bool] = None,
output_hidden_states=None, output_hidden_states: Optional[bool] = None,
return_dict=None, return_dict: Optional[bool] = None,
): ) -> Union[Tuple, MultipleChoiceModelOutput]:
r""" r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for computing the multiple choice classification loss. Indices should be in `[0, ..., Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
...@@ -1347,17 +1347,17 @@ class XLMRobertaXLForTokenClassification(XLMRobertaXLPreTrainedModel): ...@@ -1347,17 +1347,17 @@ class XLMRobertaXLForTokenClassification(XLMRobertaXLPreTrainedModel):
) )
def forward( def forward(
self, self,
input_ids=None, input_ids: Optional[torch.LongTensor] = None,
attention_mask=None, attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids=None, token_type_ids: Optional[torch.LongTensor] = None,
position_ids=None, position_ids: Optional[torch.LongTensor] = None,
head_mask=None, head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds=None, inputs_embeds: Optional[torch.FloatTensor] = None,
labels=None, labels: Optional[torch.LongTensor] = None,
output_attentions=None, output_attentions: Optional[bool] = None,
output_hidden_states=None, output_hidden_states: Optional[bool] = None,
return_dict=None, return_dict: Optional[bool] = None,
): ) -> Union[Tuple, TokenClassifierOutput]:
r""" r"""
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`. Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
...@@ -1458,18 +1458,18 @@ class XLMRobertaXLForQuestionAnswering(XLMRobertaXLPreTrainedModel): ...@@ -1458,18 +1458,18 @@ class XLMRobertaXLForQuestionAnswering(XLMRobertaXLPreTrainedModel):
) )
def forward( def forward(
self, self,
input_ids=None, input_ids: Optional[torch.LongTensor] = None,
attention_mask=None, attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids=None, token_type_ids: Optional[torch.LongTensor] = None,
position_ids=None, position_ids: Optional[torch.LongTensor] = None,
head_mask=None, head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds=None, inputs_embeds: Optional[torch.FloatTensor] = None,
start_positions=None, start_positions: Optional[torch.LongTensor] = None,
end_positions=None, end_positions: Optional[torch.LongTensor] = None,
output_attentions=None, output_attentions: Optional[bool] = None,
output_hidden_states=None, output_hidden_states: Optional[bool] = None,
return_dict=None, return_dict: Optional[bool] = None,
): ) -> Union[Tuple, QuestionAnsweringModelOutput]:
r""" r"""
start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*): start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the start of the labelled span for computing the token classification loss. Labels for position (index) of the start of the labelled span for computing the token classification loss.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment