Add many missing spaces in adjacent strings (#26751)
Add missing spaces in adjacent strings
This commit is contained in:
@@ -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)
|
||||
|
||||
Reference in New Issue
Block a user