SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

No more Tuple, List, Dict (#38797)

Browse Source 
* No more Tuple, List, Dict

* make fixup

* More style fixes

* Docstring fixes with regex replacement

* Trigger tests

* Redo fixes after rebase

* Fix copies

* [test all]

* update

* [test all]

* update

* [test all]

* make style after rebase

* Patch the hf_argparser test

* Patch the hf_argparser test

* style fixes

* style fixes

* style fixes

* Fix docstrings in Cohere test

* [test all]

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Matt
2025-06-17 19:37:18 +01:00
committed by GitHub
parent a396f4324b
commit 508a704055
1291 changed files with 14906 additions and 14941 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
examples/modular-transformers/modeling_new_task_model.py
View File

@@ -5,7 +5,7 @@
# modular_new_task_model.py file directly. One of our CI enforces this.
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
from dataclasses import dataclass
from typing import ClassVar, List, Optional, Tuple, Union
from typing import ClassVar, Optional, Union
import torch
from torch import nn
@@ -88,9 +88,9 @@ class NewTaskModelCausalLMOutputWithPast(ModelOutput):
loss: Optional[torch.FloatTensor] = None
logits: Optional[torch.FloatTensor] = None
past_key_values: Optional[Union[List[torch.FloatTensor], Cache]] = None
hidden_states: Optional[Tuple[torch.FloatTensor]] = None
attentions: Optional[Tuple[torch.FloatTensor]] = None
past_key_values: Optional[Union[list[torch.FloatTensor], Cache]] = None
hidden_states: Optional[tuple[torch.FloatTensor]] = None
attentions: Optional[tuple[torch.FloatTensor]] = None
image_hidden_states: Optional[torch.FloatTensor] = None
@@ -249,7 +249,7 @@ class NewTaskModelModel(NewTaskModelPreTrainedModel):
pixel_values: torch.FloatTensor = None,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_values: Optional[Union[List[torch.FloatTensor], Cache]] = None,
past_key_values: Optional[Union[list[torch.FloatTensor], Cache]] = None,
token_type_ids: Optional[torch.LongTensor] = None,
cache_position: Optional[torch.LongTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
@@ -259,7 +259,7 @@ class NewTaskModelModel(NewTaskModelPreTrainedModel):
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
**kwargs: Unpack[FlashAttentionKwargs],
) -> Union[Tuple, NewTaskModelModelOutputWithPast]:
) -> Union[tuple, NewTaskModelModelOutputWithPast]:
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, ...,
@@ -442,7 +442,7 @@ class NewTaskModelForNewTask(NewTaskModelPreTrainedModel, GenerationMixin):
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
num_logits_to_keep: int = 0,
) -> Union[Tuple, NewTaskModelCausalLMOutputWithPast]:
) -> Union[tuple, NewTaskModelCausalLMOutputWithPast]:
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, ...,