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

4
examples/flax/image-captioning/create_model_from_encoder_decoder_models.py
View File

@@ -37,7 +37,7 @@ class ModelArguments:
encoder_model_name_or_path: str = field(
metadata={
"help": (
"The encoder model checkpoint for weights initialization."
"The encoder model checkpoint for weights initialization. "
"Don't set if you want to train an encoder model from scratch."
)
},
@@ -45,7 +45,7 @@ class ModelArguments:
decoder_model_name_or_path: str = field(
metadata={
"help": (
"The decoder model checkpoint for weights initialization."
"The decoder model checkpoint for weights initialization. "
"Don't set if you want to train a decoder model from scratch."
)
},

8
examples/flax/image-captioning/run_image_captioning_flax.py
View File

@@ -203,7 +203,7 @@ 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."
)
},
@@ -256,7 +256,7 @@ 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 evaluation."
)
@@ -423,7 +423,7 @@ def main():
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty."
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
"Use --overwrite_output_dir to overcome."
)
@@ -685,7 +685,7 @@ def main():
eval_batch_size = int(training_args.per_device_eval_batch_size) * jax.device_count()
if training_args.block_size % train_batch_size > 0 or training_args.block_size % eval_batch_size > 0:
raise ValueError(
"`training_args.block_size` needs to be a multiple of the global train/eval batch size."
"`training_args.block_size` needs to be a multiple of the global train/eval batch size. "
f"Got {training_args.block_size}, {train_batch_size} and {eval_batch_size} respectively instead."
)

4
examples/flax/language-modeling/run_bart_dlm_flax.py
View File

@@ -487,7 +487,7 @@ def main():
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty."
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
"Use --overwrite_output_dir to overcome."
)
@@ -606,7 +606,7 @@ 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."
)

8
examples/flax/language-modeling/run_clm_flax.py
View File

@@ -190,7 +190,7 @@ 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."
)
},
@@ -368,7 +368,7 @@ def main():
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty."
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
"Use --overwrite_output_dir to overcome."
)
@@ -524,7 +524,7 @@ 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."
)
@@ -586,7 +586,7 @@ 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)

6
examples/flax/language-modeling/run_mlm_flax.py
View File

@@ -195,7 +195,7 @@ 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."
)
},
@@ -411,7 +411,7 @@ def main():
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty."
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
"Use --overwrite_output_dir to overcome."
)
@@ -556,7 +556,7 @@ 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."
)

4
examples/flax/language-modeling/run_t5_mlm_flax.py
View File

@@ -528,7 +528,7 @@ def main():
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty."
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
"Use --overwrite_output_dir to overcome."
)
@@ -647,7 +647,7 @@ 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."
)

4
examples/flax/question-answering/run_qa.py
View File

@@ -176,7 +176,7 @@ 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."
)
},
@@ -582,7 +582,7 @@ 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)

2
examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py
View File

@@ -415,7 +415,7 @@ def main():
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty."
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
"Use `--overwrite_output_dir` to overcome."
)

8
examples/flax/summarization/run_summarization_flax.py
View File

@@ -209,7 +209,7 @@ 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."
)
},
@@ -268,7 +268,7 @@ 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 evaluation."
)
@@ -451,7 +451,7 @@ def main():
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty."
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
"Use --overwrite_output_dir to overcome."
)
@@ -558,7 +558,7 @@ 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."
)

2
examples/flax/text-classification/run_flax_glue.py
View File

@@ -122,7 +122,7 @@ 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."
)
},

2
examples/flax/token-classification/run_flax_ner.py
View File

@@ -170,7 +170,7 @@ 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."
)
},

4
examples/flax/vision/run_image_classification.py
View File

@@ -180,7 +180,7 @@ 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."
)
},
@@ -291,7 +291,7 @@ def main():
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty."
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
"Use --overwrite_output_dir to overcome."
)