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

Fix input data file extension in examples (#28741)

Browse Source
This commit is contained in:
Klaus Hipp
2024-01-29 11:06:31 +01:00
committed by GitHub
parent 5649c0cbb8
commit 39fa400969
23 changed files with 49 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/pytorch/language-modeling/run_clm_no_trainer.py
View File

@@ -345,9 +345,10 @@ def main():
dataset_args = {}
if args.train_file is not None:
data_files["train"] = args.train_file
extension = args.train_file.split(".")[-1]
if args.validation_file is not None:
data_files["validation"] = args.validation_file
extension = args.train_file.split(".")[-1]
extension = args.validation_file.split(".")[-1]
if extension == "txt":
extension = "text"
dataset_args["keep_linebreaks"] = not args.no_keep_linebreaks

3
examples/pytorch/language-modeling/run_mlm_no_trainer.py
View File

@@ -351,9 +351,10 @@ def main():
data_files = {}
if args.train_file is not None:
data_files["train"] = args.train_file
extension = args.train_file.split(".")[-1]
if args.validation_file is not None:
data_files["validation"] = args.validation_file
extension = args.train_file.split(".")[-1]
extension = args.validation_file.split(".")[-1]
if extension == "txt":
extension = "text"
raw_datasets = load_dataset(extension, data_files=data_files)

3
examples/pytorch/language-modeling/run_plm.py
View File

@@ -328,9 +328,10 @@ def main():
data_files = {}
if data_args.train_file is not None:
data_files["train"] = data_args.train_file
extension = data_args.train_file.split(".")[-1]
if data_args.validation_file is not None:
data_files["validation"] = data_args.validation_file
extension = data_args.train_file.split(".")[-1]
extension = data_args.validation_file.split(".")[-1]
if extension == "txt":
extension = "text"
raw_datasets = load_dataset(extension, data_files=data_files, cache_dir=model_args.cache_dir)