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

Add use_auth to load_datasets for private datasets to PT and TF examples (#16521)

Browse Source 
* fix formatting and remove use_auth

* Add use_auth_token to Flax examples
This commit is contained in:
Karim Foda
2022-04-04 15:27:45 +01:00
committed by GitHub
parent b9a768b3ff
commit 24a85cca61
36 changed files with 544 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
examples/tensorflow/language-modeling/run_mlm.py
View File

@@ -292,17 +292,23 @@ def main():
# download the dataset.
if data_args.dataset_name is not None:
# Downloading and loading a dataset from the hub.
raw_datasets = load_dataset(data_args.dataset_name, data_args.dataset_config_name)
raw_datasets = load_dataset(
data_args.dataset_name,
data_args.dataset_config_name,
use_auth_token=True if model_args.use_auth_token else None,
)
if "validation" not in raw_datasets.keys():
raw_datasets["validation"] = load_dataset(
data_args.dataset_name,
data_args.dataset_config_name,
split=f"train[:{data_args.validation_split_percentage}%]",
use_auth_token=True if model_args.use_auth_token else None,
)
raw_datasets["train"] = load_dataset(
data_args.dataset_name,
data_args.dataset_config_name,
split=f"train[{data_args.validation_split_percentage}%:]",
use_auth_token=True if model_args.use_auth_token else None,
)
else:
data_files = {}
@@ -313,7 +319,11 @@ def main():
extension = data_args.train_file.split(".")[-1]
if extension == "txt":
extension = "text"
raw_datasets = load_dataset(extension, data_files=data_files)
raw_datasets = load_dataset(
extension,
data_files=data_files,
use_auth_token=True if model_args.use_auth_token else None,
)
# See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
# https://huggingface.co/docs/datasets/loading_datasets.html.