mirror of
https://github.com/huggingface/transformers.git
synced 2025-08-02 19:21:31 +06:00
Added missing type hints (#16103)
This commit is contained in:
Kamal Raj
GitHub
parent
efd6e9a82a
commit
1d43933fbc
@ -17,7 +17,7 @@
|
||||
import math
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
from typing import Optional, Tuple
|
||||
from typing import List, Optional, Tuple, Union
|
||||
|
||||
import torch
|
||||
import torch.utils.checkpoint
|
||||
@ -842,20 +842,20 @@ class ElectraModel(ElectraPreTrainedModel):
|
||||
)
|
||||
def forward(
|
||||
self,
|
||||
input_ids=None,
|
||||
attention_mask=None,
|
||||
token_type_ids=None,
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
encoder_hidden_states=None,
|
||||
encoder_attention_mask=None,
|
||||
past_key_values=None,
|
||||
use_cache=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
):
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
encoder_hidden_states: Optional[torch.Tensor] = None,
|
||||
encoder_attention_mask: Optional[torch.Tensor] = None,
|
||||
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
||||
use_cache: Optional[bool] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, BaseModelOutputWithCrossAttentions]:
|
||||
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
|
||||
output_hidden_states = (
|
||||
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
|
||||
@ -978,17 +978,17 @@ class ElectraForSequenceClassification(ElectraPreTrainedModel):
|
||||
)
|
||||
def forward(
|
||||
self,
|
||||
input_ids=None,
|
||||
attention_mask=None,
|
||||
token_type_ids=None,
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
labels=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
):
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
labels: Optional[torch.Tensor] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, SequenceClassifierOutput]:
|
||||
r"""
|
||||
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
|
||||
Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
|
||||
@ -1068,17 +1068,17 @@ class ElectraForPreTraining(ElectraPreTrainedModel):
|
||||
@replace_return_docstrings(output_type=ElectraForPreTrainingOutput, config_class=_CONFIG_FOR_DOC)
|
||||
def forward(
|
||||
self,
|
||||
input_ids=None,
|
||||
attention_mask=None,
|
||||
token_type_ids=None,
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
labels=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
):
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
labels: Optional[torch.Tensor] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, ElectraForPreTrainingOutput]:
|
||||
r"""
|
||||
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
|
||||
Labels for computing the ELECTRA loss. Input should be a sequence of tokens (see `input_ids` docstring)
|
||||
@ -1178,17 +1178,17 @@ class ElectraForMaskedLM(ElectraPreTrainedModel):
|
||||
)
|
||||
def forward(
|
||||
self,
|
||||
input_ids=None,
|
||||
attention_mask=None,
|
||||
token_type_ids=None,
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
labels=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
):
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
labels: Optional[torch.Tensor] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, MaskedLMOutput]:
|
||||
r"""
|
||||
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
|
||||
Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
|
||||
@ -1262,17 +1262,17 @@ class ElectraForTokenClassification(ElectraPreTrainedModel):
|
||||
)
|
||||
def forward(
|
||||
self,
|
||||
input_ids=None,
|
||||
attention_mask=None,
|
||||
token_type_ids=None,
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
labels=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
):
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
labels: Optional[torch.Tensor] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, TokenClassifierOutput]:
|
||||
r"""
|
||||
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]`.
|
||||
@ -1342,18 +1342,18 @@ class ElectraForQuestionAnswering(ElectraPreTrainedModel):
|
||||
)
|
||||
def forward(
|
||||
self,
|
||||
input_ids=None,
|
||||
attention_mask=None,
|
||||
token_type_ids=None,
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
start_positions=None,
|
||||
end_positions=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
):
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
start_positions: Optional[torch.Tensor] = None,
|
||||
end_positions: Optional[torch.Tensor] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, QuestionAnsweringModelOutput]:
|
||||
r"""
|
||||
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.
|
||||
@ -1444,17 +1444,17 @@ class ElectraForMultipleChoice(ElectraPreTrainedModel):
|
||||
)
|
||||
def forward(
|
||||
self,
|
||||
input_ids=None,
|
||||
attention_mask=None,
|
||||
token_type_ids=None,
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
labels=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
):
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
labels: Optional[torch.Tensor] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, MultipleChoiceModelOutput]:
|
||||
r"""
|
||||
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
|
||||
Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
|
||||
@ -1535,21 +1535,21 @@ class ElectraForCausalLM(ElectraPreTrainedModel):
|
||||
@replace_return_docstrings(output_type=CausalLMOutputWithCrossAttentions, config_class=_CONFIG_FOR_DOC)
|
||||
def forward(
|
||||
self,
|
||||
input_ids=None,
|
||||
attention_mask=None,
|
||||
token_type_ids=None,
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
encoder_hidden_states=None,
|
||||
encoder_attention_mask=None,
|
||||
labels=None,
|
||||
past_key_values=None,
|
||||
use_cache=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
):
|
||||
input_ids: Optional[torch.Tensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
token_type_ids: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.Tensor] = None,
|
||||
head_mask: Optional[torch.Tensor] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
encoder_hidden_states: Optional[torch.Tensor] = None,
|
||||
encoder_attention_mask: Optional[torch.Tensor] = None,
|
||||
labels: Optional[torch.Tensor] = None,
|
||||
past_key_values: Optional[List[torch.Tensor]] = None,
|
||||
use_cache: Optional[bool] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, CausalLMOutputWithCrossAttentions]:
|
||||
r"""
|
||||
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
|
||||
|
||||
Loading…
Reference in New Issue
Block a user