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

Add token arugment in example scripts (#25172)

Browse Source 
* fix

* fix

* fix

* fix

* fix

* fix

* fix

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar
2023-08-02 11:17:31 +02:00
committed by GitHub
parent c6a8768dab
commit 149cb0cce2
43 changed files with 987 additions and 420 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
examples/tensorflow/contrastive-image-text/run_clip.py
View File

@@ -26,6 +26,7 @@ Text models: BERT, ROBERTa (https://huggingface.co/models?filter=fill-mask)
import logging
import os
import sys
import warnings
from dataclasses import dataclass, field
from typing import Optional
@@ -92,15 +93,21 @@ class ModelArguments:
default=True,
metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
)
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`."
},
)
freeze_vision_model: bool = field(
default=False, metadata={"help": "Whether to freeze the vision model parameters or not."}
)
@@ -245,6 +252,12 @@ 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
if model_args.model_name_or_path is not None:
if model_args.vision_model_name_or_path is not None or model_args.text_model_name_or_path is not None:
raise ValueError(
@@ -315,7 +328,7 @@ 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 = {}
@@ -332,7 +345,7 @@ 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.
@@ -362,14 +375,14 @@ def main():
model_args.image_processor_name or model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
with training_args.strategy.scope():
model = TFAutoModel.from_pretrained(
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
# Load image_processor, in this script we only use this to get the mean and std for normalization.
@@ -377,14 +390,14 @@ def main():
model_args.image_processor_name or model_args.vision_model_name_or_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
with training_args.strategy.scope():
model = TFVisionTextDualEncoderModel.from_vision_text_pretrained(
vision_model_name_or_path=model_args.vision_model_name_or_path,
text_model_name_or_path=model_args.text_model_name_or_path,
cache_dir=model_args.cache_dir,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
config = model.config

29
examples/tensorflow/image-classification/run_image_classification.py
View File

@@ -23,6 +23,7 @@ import json
import logging
import os
import sys
import warnings
from dataclasses import dataclass, field
from typing import Optional
@@ -157,15 +158,21 @@ class ModelArguments:
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
image_processor_name: str = field(default=None, metadata={"help": "Name or path of preprocessor config."})
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`."
},
)
ignore_mismatched_sizes: bool = field(
default=False,
metadata={"help": "Will enable to load a pretrained model whose head dimensions are different."},
@@ -226,6 +233,12 @@ 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
if not (training_args.do_train or training_args.do_eval or training_args.do_predict):
exit("Must specify at least one of --do_train, --do_eval or --do_predict!")
@@ -275,7 +288,7 @@ def main():
data_args.dataset_config_name,
cache_dir=model_args.cache_dir,
task="image-classification",
use_auth_token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
data_files = {}
@@ -309,13 +322,13 @@ def main():
finetuning_task="image-classification",
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
image_processor = AutoImageProcessor.from_pretrained(
model_args.image_processor_name or model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# If we don't have a validation split, split off a percentage of train as validation.
@@ -435,7 +448,7 @@ def main():
from_pt=bool(".bin" in model_path),
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
ignore_mismatched_sizes=model_args.ignore_mismatched_sizes,
)
num_replicas = training_args.strategy.num_replicas_in_sync

33
examples/tensorflow/language-modeling/run_clm.py
View File

@@ -30,6 +30,7 @@ import math
import os
import random
import sys
import warnings
from dataclasses import dataclass, field
from itertools import chain
from pathlib import Path
@@ -112,15 +113,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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`."
},
)
def __post_init__(self):
if self.config_overrides is not None and (self.config_name is not None or self.model_name_or_path is not None):
@@ -220,6 +227,12 @@ 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="tensorflow")
@@ -287,7 +300,7 @@ 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 raw_datasets.keys():
raw_datasets["validation"] = load_dataset(
@@ -295,14 +308,14 @@ 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,
)
raw_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 = {}
@@ -323,7 +336,7 @@ 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,
**dataset_args,
)
# If no validation data is there, validation_split_percentage will be used to divide the dataset.
@@ -333,7 +346,7 @@ 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,
**dataset_args,
)
raw_datasets["train"] = load_dataset(
@@ -341,7 +354,7 @@ 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,
**dataset_args,
)
# See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at

29
examples/tensorflow/language-modeling/run_mlm.py
View File

@@ -28,6 +28,7 @@ import math
import os
import random
import sys
import warnings
from dataclasses import dataclass, field
from itertools import chain
from pathlib import Path
@@ -110,15 +111,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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`."
},
)
def __post_init__(self):
if self.config_overrides is not None and (self.config_name is not None or self.model_name_or_path is not None):
@@ -226,6 +233,12 @@ 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_mlm", model_args, data_args, framework="tensorflow")
@@ -296,20 +309,20 @@ def main():
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,
token=model_args.token,
)
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,
token=model_args.token,
)
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,
token=model_args.token,
)
else:
data_files = {}
@@ -323,7 +336,7 @@ def main():
raw_datasets = load_dataset(
extension,
data_files=data_files,
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

31
examples/tensorflow/multiple-choice/run_swag.py
View File

@@ -22,6 +22,7 @@ import json
import logging
import os
import sys
import warnings
from dataclasses import dataclass, field
from itertools import chain
from pathlib import Path
@@ -146,15 +147,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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
@@ -239,6 +246,12 @@ 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_swag", model_args, data_args, framework="tensorflow")
@@ -301,7 +314,7 @@ 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,
)
else:
# Downloading and loading the swag dataset from the hub.
@@ -309,7 +322,7 @@ def main():
"swag",
"regular",
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.
@@ -335,14 +348,14 @@ def main():
config_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# endregion
@@ -428,7 +441,7 @@ def main():
config=config,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
num_replicas = training_args.strategy.num_replicas_in_sync

31
examples/tensorflow/question-answering/run_qa.py
View File

@@ -22,6 +22,7 @@ import json
import logging
import os
import sys
import warnings
from dataclasses import dataclass, field
from pathlib import Path
from typing import Optional
@@ -77,15 +78,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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
@@ -245,6 +252,12 @@ 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_qa", model_args, data_args, framework="tensorflow")
@@ -304,7 +317,7 @@ 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,
)
else:
data_files = {}
@@ -323,7 +336,7 @@ def main():
data_files=data_files,
field="data",
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.
@@ -338,14 +351,14 @@ def main():
model_args.config_name if model_args.config_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=True,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# endregion
@@ -625,7 +638,7 @@ def main():
config=config,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
if training_args.do_train:
training_dataset = model.prepare_tf_dataset(

31
examples/tensorflow/summarization/run_summarization.py
View File

@@ -22,6 +22,7 @@ import json
import logging
import os
import sys
import warnings
from dataclasses import dataclass, field
from typing import Optional
@@ -99,15 +100,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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
@@ -287,6 +294,12 @@ 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_summarization", model_args, data_args, framework="tensorflow")
@@ -355,7 +368,7 @@ 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,
)
else:
data_files = {}
@@ -372,7 +385,7 @@ 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.
@@ -388,14 +401,14 @@ def main():
model_args.config_name if model_args.config_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
prefix = data_args.source_prefix if data_args.source_prefix is not None else ""
@@ -513,7 +526,7 @@ def main():
config=config,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch

29
examples/tensorflow/text-classification/run_glue.py
View File

@@ -20,6 +20,7 @@ import json
import logging
import os
import sys
import warnings
from dataclasses import dataclass, field
from typing import Optional
@@ -164,15 +165,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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`."
},
)
# endregion
@@ -192,6 +199,12 @@ 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_glue", model_args, data_args, framework="tensorflow")
@@ -242,7 +255,7 @@ def main():
"glue",
data_args.task_name,
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 at
# https://huggingface.co/docs/datasets/loading_datasets.html.
@@ -284,14 +297,14 @@ def main():
finetuning_task=data_args.task_name,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# endregion
@@ -374,7 +387,7 @@ def main():
config=config,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# endregion

31
examples/tensorflow/text-classification/run_text_classification.py
View File

@@ -20,6 +20,7 @@ import json
import logging
import os
import sys
import warnings
from dataclasses import dataclass, field
from pathlib import Path
from typing import Optional
@@ -170,15 +171,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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`."
},
)
# endregion
@@ -198,6 +205,12 @@ 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_text_classification", model_args, data_args, framework="tensorflow")
@@ -258,7 +271,7 @@ def main():
"csv",
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,
)
else:
# Loading a dataset from local json files
@@ -301,20 +314,20 @@ def main():
num_labels=num_labels,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
else:
config = AutoConfig.from_pretrained(
config_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# endregion
@@ -402,7 +415,7 @@ def main():
config=config,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# endregion

25
examples/tensorflow/token-classification/run_ner.py
View File

@@ -21,6 +21,7 @@ import json
import logging
import os
import random
import warnings
from dataclasses import dataclass, field
from typing import Optional
@@ -75,15 +76,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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
@@ -196,6 +203,12 @@ def main():
parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TFTrainingArguments))
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_ner", model_args, data_args, framework="tensorflow")
@@ -228,7 +241,7 @@ def main():
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,
token=model_args.token,
)
else:
data_files = {}
@@ -240,7 +253,7 @@ def main():
raw_datasets = load_dataset(
extension,
data_files=data_files,
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.

31
examples/tensorflow/translation/run_translation.py
View File

@@ -22,6 +22,7 @@ import json
import logging
import os
import sys
import warnings
from dataclasses import dataclass, field
from typing import Optional
@@ -93,15 +94,21 @@ class ModelArguments:
default="main",
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
)
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
@@ -268,6 +275,12 @@ 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_translation", model_args, data_args, framework="tensorflow")
@@ -322,7 +335,7 @@ 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,
)
else:
data_files = {}
@@ -336,7 +349,7 @@ 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
@@ -352,14 +365,14 @@ def main():
model_args.config_name if model_args.config_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
prefix = data_args.source_prefix if data_args.source_prefix is not None else ""
@@ -466,7 +479,7 @@ def main():
config=config,
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=True if model_args.use_auth_token else None,
token=model_args.token,
)
# We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch