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

26
examples/pytorch/text-classification/run_glue.py
View File

@@ -252,11 +252,19 @@ def main():
# download the dataset.
if data_args.task_name is not None:
# Downloading and loading a dataset from the hub.
raw_datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)
raw_datasets = load_dataset(
"glue",
data_args.task_name,
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
)
elif 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, cache_dir=model_args.cache_dir
data_args.dataset_name,
data_args.dataset_config_name,
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
)
else:
# Loading a dataset from your local files.
@@ -281,10 +289,20 @@ def main():
if data_args.train_file.endswith(".csv"):
# Loading a dataset from local csv files
raw_datasets = load_dataset("csv", data_files=data_files, cache_dir=model_args.cache_dir)
raw_datasets = load_dataset(
"csv",
data_files=data_files,
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
)
else:
# Loading a dataset from local json files
raw_datasets = load_dataset("json", data_files=data_files, cache_dir=model_args.cache_dir)
raw_datasets = load_dataset(
"json",
data_files=data_files,
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
)
# See more about loading any type of standard or custom dataset at
# https://huggingface.co/docs/datasets/loading_datasets.html.

30
examples/pytorch/text-classification/run_xnli.py
View File

@@ -213,19 +213,41 @@ def main():
# Downloading and loading xnli dataset from the hub.
if training_args.do_train:
if model_args.train_language is None:
train_dataset = load_dataset("xnli", model_args.language, split="train", cache_dir=model_args.cache_dir)
train_dataset = load_dataset(
"xnli",
model_args.language,
split="train",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
)
else:
train_dataset = load_dataset(
"xnli", model_args.train_language, split="train", cache_dir=model_args.cache_dir
"xnli",
model_args.train_language,
split="train",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
)
label_list = train_dataset.features["label"].names
if training_args.do_eval:
eval_dataset = load_dataset("xnli", model_args.language, split="validation", cache_dir=model_args.cache_dir)
eval_dataset = load_dataset(
"xnli",
model_args.language,
split="validation",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
)
label_list = eval_dataset.features["label"].names
if training_args.do_predict:
predict_dataset = load_dataset("xnli", model_args.language, split="test", cache_dir=model_args.cache_dir)
predict_dataset = load_dataset(
"xnli",
model_args.language,
split="test",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
)
label_list = predict_dataset.features["label"].names
# Labels