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/language-modeling/run_clm.py
View File

@@ -132,7 +132,7 @@ 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."
)
},
@@ -151,7 +151,7 @@ class ModelArguments:
default=False,
metadata={
"help": (
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded."
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded. "
"set True will benefit LLM loading time and RAM consumption."
)
},
@@ -424,7 +424,7 @@ def main():
tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path, **tokenizer_kwargs)
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."
)
@@ -506,7 +506,7 @@ def main():
else:
if data_args.block_size > tokenizer.model_max_length:
logger.warning(
f"The block_size passed ({data_args.block_size}) is larger than the maximum length for the model"
f"The block_size passed ({data_args.block_size}) is larger than the maximum length for the model "
f"({tokenizer.model_max_length}). Using block_size={tokenizer.model_max_length}."
)
block_size = min(data_args.block_size, tokenizer.model_max_length)

10
examples/pytorch/language-modeling/run_clm_no_trainer.py
View File

@@ -199,7 +199,7 @@ 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."
),
)
@@ -226,7 +226,7 @@ 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."
),
)
@@ -234,7 +234,7 @@ def parse_args():
"--low_cpu_mem_usage",
action="store_true",
help=(
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded."
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded. "
"If passed, LLM loading time and RAM consumption will be benefited."
),
)
@@ -398,7 +398,7 @@ 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."
)
@@ -449,7 +449,7 @@ def main():
else:
if args.block_size > tokenizer.model_max_length:
logger.warning(
f"The block_size passed ({args.block_size}) is larger than the maximum length for the model"
f"The block_size passed ({args.block_size}) is larger than the maximum length for the model "
f"({tokenizer.model_max_length}). Using block_size={tokenizer.model_max_length}."
)
block_size = min(args.block_size, tokenizer.model_max_length)

8
examples/pytorch/language-modeling/run_mlm.py
View File

@@ -128,7 +128,7 @@ 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."
)
},
@@ -137,7 +137,7 @@ class ModelArguments:
default=False,
metadata={
"help": (
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded."
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded. "
"set True will benefit LLM loading time and RAM consumption."
)
},
@@ -417,7 +417,7 @@ def main():
tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path, **tokenizer_kwargs)
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."
)
@@ -462,7 +462,7 @@ def main():
else:
if data_args.max_seq_length > tokenizer.model_max_length:
logger.warning(
f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the "
f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
)
max_seq_length = min(data_args.max_seq_length, tokenizer.model_max_length)

10
examples/pytorch/language-modeling/run_mlm_no_trainer.py
View File

@@ -206,7 +206,7 @@ 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."
),
)
@@ -233,7 +233,7 @@ 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."
),
)
@@ -241,7 +241,7 @@ def parse_args():
"--low_cpu_mem_usage",
action="store_true",
help=(
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded."
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded. "
"If passed, LLM loading time and RAM consumption will be benefited."
),
)
@@ -395,7 +395,7 @@ 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."
)
@@ -434,7 +434,7 @@ def main():
else:
if args.max_seq_length > tokenizer.model_max_length:
logger.warning(
f"The max_seq_length passed ({args.max_seq_length}) is larger than the maximum length for the"
f"The max_seq_length passed ({args.max_seq_length}) is larger than the maximum length for the "
f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
)
max_seq_length = min(args.max_seq_length, tokenizer.model_max_length)

6
examples/pytorch/language-modeling/run_plm.py
View File

@@ -115,7 +115,7 @@ class ModelArguments:
default=False,
metadata={
"help": (
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded."
"It is an option to create the model as an empty shell, then only materialize its parameters when the pretrained weights are loaded. "
"set True will benefit LLM loading time and RAM consumption."
)
},
@@ -385,7 +385,7 @@ def main():
tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path, **tokenizer_kwargs)
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."
)
@@ -419,7 +419,7 @@ def main():
if data_args.max_seq_length > tokenizer.model_max_length:
logger.warning(
f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the "
f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
)
max_seq_length = min(data_args.max_seq_length, tokenizer.model_max_length)