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

Add many missing spaces in adjacent strings (#26751)

Browse Source 
Add missing spaces in adjacent strings
This commit is contained in:
Tom Aarsen
2023-10-12 10:28:40 +02:00
committed by GitHub
parent 3bc65505fc
commit 40ea9ab2a1
154 changed files with 331 additions and 331 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/pytorch/summarization/run_summarization.py
View File

@@ -120,7 +120,7 @@ class ModelArguments:
metadata={
"help": (
"Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
"should only be set to `True` for repositories you trust and in which you have read the code, as it will"
"should only be set to `True` for repositories you trust and in which you have read the code, as it will "
"execute code present on the Hub on your local machine."
)
},
@@ -205,7 +205,7 @@ class DataTrainingArguments:
metadata={
"help": (
"The maximum total sequence length for validation target text after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded. Will default to `max_target_length`."
"than this will be truncated, sequences shorter will be padded. Will default to `max_target_length`. "
"This argument is also used to override the ``max_length`` param of ``model.generate``, which is used "
"during ``evaluate`` and ``predict``."
)
@@ -271,7 +271,7 @@ class DataTrainingArguments:
default=None,
metadata={
"help": (
"The token to force as the first generated token after the decoder_start_token_id."
"The token to force as the first generated token after the decoder_start_token_id. "
"Useful for multilingual models like mBART where the first generated token"
"needs to be the target language token (Usually it is the target language token)"
)
@@ -556,7 +556,7 @@ def main():
if training_args.label_smoothing_factor > 0 and not hasattr(model, "prepare_decoder_input_ids_from_labels"):
logger.warning(
"label_smoothing is enabled but the `prepare_decoder_input_ids_from_labels` method is not defined for"
"label_smoothing is enabled but the `prepare_decoder_input_ids_from_labels` method is not defined for "
f"`{model.__class__.__name__}`. This will lead to loss being calculated twice and will take up more memory"
)

8
examples/pytorch/summarization/run_summarization_no_trainer.py
View File

@@ -146,7 +146,7 @@ def parse_args():
default=128,
help=(
"The maximum total sequence length for target text after "
"tokenization. Sequences longer than this will be truncated, sequences shorter will be padded."
"tokenization. Sequences longer than this will be truncated, sequences shorter will be padded. "
"during ``evaluate`` and ``predict``."
),
)
@@ -272,7 +272,7 @@ def parse_args():
default=False,
help=(
"Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
"should only be set to `True` for repositories you trust and in which you have read the code, as it will"
"should only be set to `True` for repositories you trust and in which you have read the code, as it will "
"execute code present on the Hub on your local machine."
),
)
@@ -299,7 +299,7 @@ def parse_args():
default="all",
help=(
'The integration to report the results and logs to. Supported platforms are `"tensorboard"`,'
' `"wandb"`, `"comet_ml"` and `"clearml"`. Use `"all"` (default) to report to all integrations.'
' `"wandb"`, `"comet_ml"` and `"clearml"`. Use `"all"` (default) to report to all integrations. '
"Only applicable when `--with_tracking` is passed."
),
)
@@ -433,7 +433,7 @@ def main():
)
else:
raise ValueError(
"You are instantiating a new tokenizer from scratch. This is not supported by this script."
"You are instantiating a new tokenizer from scratch. This is not supported by this script. "
"You can do it from another script, save it, and load it from here, using --tokenizer_name."
)