Skip to content

Add token arugment in example scripts #25172

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Aug 2, 2023
Merged

Add token arugment in example scripts #25172

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
4c311ef
fix
ydshieh Aug 1, 2023
4f8575a
fix
ydshieh Aug 1, 2023
2b0eeea
fix
ydshieh Aug 1, 2023
b1583e5
fix
ydshieh Aug 2, 2023
feb2bd7
fix
ydshieh Aug 2, 2023
75c72c3
fix
ydshieh Aug 2, 2023
baa800c
fix
ydshieh Aug 2, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 22 additions & 9 deletions examples/flax/image-captioning/run_image_captioning_flax.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import os
import sys
import time
import warnings
from dataclasses import asdict, dataclass, field
from enum import Enum
from functools import partial
Expand Down Expand Up @@ -182,15 +183,21 @@ class ModelArguments:
)
},
)
use_auth_token: bool = field(
default=False,
token: str = field(
default=None,
metadata={
"help": (
"Will use the token generated when running `huggingface-cli login` (necessary to use this script "
"with private models)."
"The token to use as HTTP bearer authorization for remote files. If not specified, will use the token "
"generated when running `huggingface-cli login` (stored in `~/.huggingface`)."
)
},
)
use_auth_token: bool = field(
default=None,
metadata={
"help": "The `use_auth_token` argument is deprecated and will be removed in v4.34. Please use `token`."
},
)


@dataclass
Expand Down Expand Up @@ -389,6 +396,12 @@ def main():
else:
model_args, data_args, training_args = parser.parse_args_into_dataclasses()

if model_args.use_auth_token is not None:
warnings.warn("The `use_auth_token` argument is deprecated and will be removed in v4.34.", FutureWarning)
if model_args.token is not None:
raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
model_args.token = model_args.use_auth_token

# Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
# information sent is the one passed as arguments along with your Python/PyTorch versions.
send_example_telemetry("run_image_captioning", model_args, data_args, framework="flax")
Expand Down Expand Up @@ -448,7 +461,7 @@ def main():
cache_dir=model_args.cache_dir,
keep_in_memory=False,
data_dir=data_args.data_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
data_files = {}
Expand All @@ -465,7 +478,7 @@ def main():
extension,
data_files=data_files,
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# 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.
Expand All @@ -475,18 +488,18 @@ def main():
model_args.model_name_or_path,
seed=training_args.seed,
dtype=getattr(jnp, model_args.dtype),
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
image_processor = AutoImageProcessor.from_pretrained(
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
tokenizer = AutoTokenizer.from_pretrained(
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
tokenizer.pad_token = tokenizer.convert_ids_to_tokens(model.config.pad_token_id)

Expand Down
43 changes: 28 additions & 15 deletions examples/flax/language-modeling/run_bart_dlm_flax.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
import os
import sys
import time
import warnings
from dataclasses import asdict, dataclass, field
from enum import Enum
from itertools import chain
Expand Down Expand Up @@ -168,15 +169,21 @@ class ModelArguments:
)
},
)
use_auth_token: bool = field(
default=False,
token: str = field(
default=None,
metadata={
"help": (
"Will use the token generated when running `huggingface-cli login` (necessary to use this script "
"with private models)."
"The token to use as HTTP bearer authorization for remote files. If not specified, will use the token "
"generated when running `huggingface-cli login` (stored in `~/.huggingface`)."
)
},
)
use_auth_token: bool = field(
default=None,
metadata={
"help": "The `use_auth_token` argument is deprecated and will be removed in v4.34. Please use `token`."
},
)


@dataclass
Expand Down Expand Up @@ -463,6 +470,12 @@ def main():
else:
model_args, data_args, training_args = parser.parse_args_into_dataclasses()

if model_args.use_auth_token is not None:
warnings.warn("The `use_auth_token` argument is deprecated and will be removed in v4.34.", FutureWarning)
if model_args.token is not None:
raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
model_args.token = model_args.use_auth_token

# Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
# information sent is the one passed as arguments along with your Python/PyTorch versions.
send_example_telemetry("run_bart_dlm", model_args, data_args, framework="flax")
Expand Down Expand Up @@ -517,7 +530,7 @@ def main():
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,
token=model_args.token,
)

if "validation" not in datasets.keys():
Expand All @@ -526,14 +539,14 @@ def main():
data_args.dataset_config_name,
split=f"train[:{data_args.validation_split_percentage}%]",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
datasets["train"] = load_dataset(
data_args.dataset_name,
data_args.dataset_config_name,
split=f"train[{data_args.validation_split_percentage}%:]",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
data_files = {}
Expand All @@ -548,7 +561,7 @@ def main():
extension,
data_files=data_files,
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)

if "validation" not in datasets.keys():
Expand All @@ -557,14 +570,14 @@ def main():
data_files=data_files,
split=f"train[:{data_args.validation_split_percentage}%]",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
datasets["train"] = load_dataset(
extension,
data_files=data_files,
split=f"train[{data_args.validation_split_percentage}%:]",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# 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.
Expand All @@ -576,14 +589,14 @@ def main():
model_args.tokenizer_name,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
elif model_args.model_name_or_path:
tokenizer = AutoTokenizer.from_pretrained(
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
raise ValueError(
Expand All @@ -596,13 +609,13 @@ def main():
model_args.config_name,
cache_dir=model_args.cache_dir,
vocab_size=len(tokenizer),
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
elif model_args.model_name_or_path:
config = BartConfig.from_pretrained(
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
config = CONFIG_MAPPING[model_args.model_type]()
Expand Down Expand Up @@ -707,7 +720,7 @@ def group_texts(examples):
config=config,
seed=training_args.seed,
dtype=getattr(jnp, model_args.dtype),
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
config.vocab_size = len(tokenizer)
Expand Down
43 changes: 28 additions & 15 deletions examples/flax/language-modeling/run_clm_flax.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import os
import sys
import time
import warnings
from dataclasses import asdict, dataclass, field
from enum import Enum
from itertools import chain
Expand Down Expand Up @@ -169,15 +170,21 @@ class ModelArguments:
)
},
)
use_auth_token: bool = field(
default=False,
token: str = field(
default=None,
metadata={
"help": (
"Will use the token generated when running `huggingface-cli login` (necessary to use this script "
"with private models)."
"The token to use as HTTP bearer authorization for remote files. If not specified, will use the token "
"generated when running `huggingface-cli login` (stored in `~/.huggingface`)."
)
},
)
use_auth_token: bool = field(
default=None,
metadata={
"help": "The `use_auth_token` argument is deprecated and will be removed in v4.34. Please use `token`."
},
)


@dataclass
Expand Down Expand Up @@ -334,6 +341,12 @@ def main():
else:
model_args, data_args, training_args = parser.parse_args_into_dataclasses()

if model_args.use_auth_token is not None:
warnings.warn("The `use_auth_token` argument is deprecated and will be removed in v4.34.", FutureWarning)
if model_args.token is not None:
raise ValueError("`token` and `use_auth_token` are both specified. Please set only the argument `token`.")
model_args.token = model_args.use_auth_token

# Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
# information sent is the one passed as arguments along with your Python/PyTorch versions.
send_example_telemetry("run_clm", model_args, data_args, framework="flax")
Expand Down Expand Up @@ -397,7 +410,7 @@ def main():
data_args.dataset_config_name,
cache_dir=model_args.cache_dir,
keep_in_memory=False,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)

if "validation" not in dataset.keys():
Expand All @@ -406,14 +419,14 @@ def main():
data_args.dataset_config_name,
split=f"train[:{data_args.validation_split_percentage}%]",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
dataset["train"] = load_dataset(
data_args.dataset_name,
data_args.dataset_config_name,
split=f"train[{data_args.validation_split_percentage}%:]",
cache_dir=model_args.cache_dir,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
data_files = {}
Expand All @@ -431,7 +444,7 @@ def main():
data_files=data_files,
cache_dir=model_args.cache_dir,
**dataset_args,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)

if "validation" not in dataset.keys():
Expand All @@ -441,15 +454,15 @@ def main():
split=f"train[:{data_args.validation_split_percentage}%]",
cache_dir=model_args.cache_dir,
**dataset_args,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
dataset["train"] = load_dataset(
extension,
data_files=data_files,
split=f"train[{data_args.validation_split_percentage}%:]",
cache_dir=model_args.cache_dir,
**dataset_args,
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# 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.
Expand All @@ -463,13 +476,13 @@ def main():
config = AutoConfig.from_pretrained(
model_args.config_name,
cache_dir=model_args.cache_dir,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
elif model_args.model_name_or_path:
config = AutoConfig.from_pretrained(
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
config = CONFIG_MAPPING[model_args.model_type]()
Expand All @@ -480,14 +493,14 @@ def main():
model_args.tokenizer_name,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
elif model_args.model_name_or_path:
tokenizer = AutoTokenizer.from_pretrained(
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
raise ValueError(
Expand All @@ -501,7 +514,7 @@ def main():
config=config,
seed=training_args.seed,
dtype=getattr(jnp, model_args.dtype),
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
model = FlaxAutoModelForCausalLM.from_config(
Expand Down
Loading