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

Fix Bart type hints #16297

Merged
merged 6 commits into from
Apr 1, 2022
Merged

Fix Bart type hints #16297

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2f2d77c
Add type hints to PLBart PyTorch
gchhablani Mar 21, 2022
84a4833
Merge remote-tracking branch 'upstream/master' into add_type_hints_pl…
gchhablani Mar 21, 2022
cc4fa88
Remove pending merge conflicts
gchhablani Mar 21, 2022
b89d2dc
Merge remote-tracking branch 'upstream/main' into add_type_hints_plba…
gchhablani Mar 30, 2022
aa8c73e
Fix PLBart Type Hints
gchhablani Mar 30, 2022
5982977
Add changes from review
gchhablani 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
80 changes: 40 additions & 40 deletions src/transformers/models/plbart/modeling_plbart.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
import copy
import math
import random
from typing import List, Optional, Tuple, Union
from typing import Any, Dict, List, Optional, Tuple, Union

import torch
import torch.utils.checkpoint
Expand Down Expand Up @@ -1142,21 +1142,21 @@ def get_decoder(self):
)
def forward(
self,
input_ids=None,
attention_mask=None,
decoder_input_ids=None,
decoder_attention_mask=None,
head_mask=None,
decoder_head_mask=None,
cross_attn_head_mask=None,
encoder_outputs=None,
past_key_values=None,
inputs_embeds=None,
input_ids: Optional[torch.LongTensor] = None,
attention_mask: Optional[torch.LongTensor] = None,
decoder_input_ids: Optional[torch.LongTensor] = None,
decoder_attention_mask: Optional[torch.Tensor] = None,
head_mask: Optional[torch.Tensor] = None,
decoder_head_mask: Optional[torch.LongTensor] = None,
cross_attn_head_mask: Optional[torch.Tensor] = None,
encoder_outputs: Optional[List[torch.FloatTensor]] = None,
past_key_values: Optional[List[torch.FloatTensor]] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
decoder_inputs_embeds=None,
use_cache=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
use_cache: Optional[bool] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
):
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
output_hidden_states = (
Expand Down Expand Up @@ -1271,23 +1271,23 @@ def set_output_embeddings(self, new_embeddings):
@add_end_docstrings(PLBART_GENERATION_EXAMPLE)
def forward(
self,
input_ids=None,
attention_mask=None,
decoder_input_ids=None,
decoder_attention_mask=None,
head_mask=None,
decoder_head_mask=None,
cross_attn_head_mask=None,
encoder_outputs=None,
past_key_values=None,
inputs_embeds=None,
input_ids: Optional[torch.LongTensor] = None,
attention_mask: Optional[torch.LongTensor] = None,
decoder_input_ids: Optional[torch.LongTensor] = None,
decoder_attention_mask: Optional[torch.Tensor] = None,
head_mask: Optional[torch.Tensor] = None,
decoder_head_mask: Optional[torch.LongTensor] = None,
cross_attn_head_mask: Optional[torch.Tensor] = None,
encoder_outputs: Optional[List[torch.FloatTensor]] = None,
past_key_values: Optional[List[torch.FloatTensor]] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
decoder_inputs_embeds=None,
labels=None,
use_cache=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,
):
labels: Optional[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[torch.Tensor], Seq2SeqLMOutput]:
r"""
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
Expand Down Expand Up @@ -1345,16 +1345,16 @@ def forward(

def prepare_inputs_for_generation(
self,
decoder_input_ids,
past=None,
attention_mask=None,
head_mask=None,
decoder_head_mask=None,
cross_attn_head_mask=None,
use_cache=None,
encoder_outputs=None,
decoder_input_ids: torch.LongTensor,
past: Optional[List[torch.FloatTensor]] = None,
attention_mask: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.Tensor] = None,
decoder_head_mask: Optional[torch.Tensor] = None,
cross_attn_head_mask: Optional[torch.Tensor] = None,
use_cache: Optional[bool] = None,
encoder_outputs: Optional[List[torch.FloatTensor]] = None,
**kwargs # TODO: Check if this is needed. It is unused?
):
) -> Dict[str, Any]:
# cut decoder_input_ids if past is used
if past is not None:
decoder_input_ids = decoder_input_ids[:, -1:]
Expand Down