Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adding missing type hints for BigBird model #16555

Merged
merged 16 commits into from
Apr 5, 2022
Merged

Adding missing type hints for BigBird model #16555

Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
8357e88
added type hints for mbart tensorflow tf implementation
reichenbch Mar 20, 2022
ef9ef21
Adding missing type hints for mBART model
reichenbch Mar 20, 2022
5b64448
Missing Type hints - correction
reichenbch Mar 21, 2022
92f5c84
Code fixup using make quality tests
reichenbch Mar 21, 2022
33d95f0
Hint types - typo error
reichenbch Mar 21, 2022
46375b4
make fix-copies and make fixup
Rocketknight1 Mar 21, 2022
52fb2b3
type hints
reichenbch Mar 23, 2022
198a01d
Merge branch 'missing-type-hints-mBART' of https://github.com/reichen…
reichenbch Mar 23, 2022
9d8021c
updated files
reichenbch Mar 23, 2022
0325d90
type hints update
reichenbch Mar 26, 2022
09e3808
Merge branch 'huggingface:main' into missing-type-hints-mBART
reichenbch Mar 27, 2022
bc85442
making dependent modesls coherent
reichenbch Mar 27, 2022
70a406a
Merge branch 'missing-type-hints-mBART' of https://github.com/reichen…
reichenbch Mar 27, 2022
363d6ce
Type hints for BigBird
reichenbch Mar 30, 2022
0e58f4d
removing typos
reichenbch Apr 1, 2022
949ebda
Merge branch 'huggingface:main' into missing-type-hints-BigBird
reichenbch Apr 1, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
202 changes: 101 additions & 101 deletions src/transformers/models/big_bird/modeling_big_bird.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
import math
import os
from dataclasses import dataclass
from typing import Optional, Tuple
from typing import Optional, Tuple, Union

import numpy as np
import torch
Expand Down Expand Up @@ -1592,7 +1592,7 @@ def forward(
to_mask=None,
blocked_encoder_mask=None,
return_dict=True,
):
) -> Union[BaseModelOutputWithPastAndCrossAttentions, Tuple]:
all_hidden_states = () if output_hidden_states else None
all_self_attentions = () if output_attentions else None
all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
Expand Down Expand Up @@ -1986,20 +1986,20 @@ def set_attention_type(self, value: str):
)
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: torch.LongTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
past_key_values: Optional[Tuple[Tuple[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[BaseModelOutputWithPoolingAndCrossAttentions, Tuple[torch.FloatTensor]]:
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
Expand Down Expand Up @@ -2280,18 +2280,18 @@ def set_output_embeddings(self, new_embeddings):
@replace_return_docstrings(output_type=BigBirdForPreTrainingOutput, 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,
next_sentence_label=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
):
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.FloatTensor] = None,
next_sentence_label: Optional[torch.LongTensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[BigBirdForPreTrainingOutput, Tuple[torch.FloatTensor]]:
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, ...,
Expand Down Expand Up @@ -2395,19 +2395,19 @@ def set_output_embeddings(self, new_embeddings):
)
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,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
):
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[MaskedLMOutput, Tuple[torch.FloatTensor]]:
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, ...,
Expand Down Expand Up @@ -2493,21 +2493,21 @@ def set_output_embeddings(self, new_embeddings):
@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,
past_key_values=None,
labels=None,
use_cache=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
):
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
labels: Optional[torch.LongTensor] = None,
use_cache: Optional[bool] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[CausalLMOutputWithCrossAttentions, Tuple[torch.FloatTensor]]:
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
Expand Down Expand Up @@ -2664,17 +2664,17 @@ def __init__(self, config):
)
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: torch.LongTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[SequenceClassifierOutput, Tuple[torch.FloatTensor]]:
r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
Expand Down Expand Up @@ -2762,17 +2762,17 @@ def __init__(self, config):
)
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: torch.LongTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[MultipleChoiceModelOutput, Tuple[torch.FloatTensor]]:
r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
Expand Down Expand Up @@ -2858,17 +2858,17 @@ def __init__(self, config):
)
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: torch.LongTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[TokenClassifierOutput, Tuple[torch.FloatTensor]]:
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]`.
Expand Down Expand Up @@ -2957,19 +2957,19 @@ def __init__(self, config, add_pooling_layer=False):
)
def forward(
self,
input_ids=None,
attention_mask=None,
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
question_lengths=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,
):
token_type_ids: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.FloatTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
start_positions: Optional[torch.LongTensor] = None,
end_positions: Optional[torch.LongTensor] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[BigBirdForQuestionAnsweringModelOutput, Tuple[torch.FloatTensor]]:
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.
Expand Down