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

37
examples/pytorch/language-modeling/run_plm.py
View File

@@ -22,6 +22,7 @@ import logging
import math
import os
import sys
import warnings
from dataclasses import dataclass, field
from itertools import chain
from typing import Optional
@@ -95,15 +96,21 @@ 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`."
},
)
low_cpu_mem_usage: bool = field(
default=False,
metadata={
@@ -229,6 +236,12 @@ 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_plm", model_args, data_args)
@@ -291,7 +304,7 @@ 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(
@@ -299,14 +312,14 @@ 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 = {}
@@ -325,14 +338,14 @@ 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,
)
raw_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
@@ -346,7 +359,7 @@ def main():
config_kwargs = {
"cache_dir": model_args.cache_dir,
"revision": model_args.model_revision,
"use_auth_token": True if model_args.use_auth_token else None,
"token": model_args.token,
}
if model_args.config_name:
config = AutoConfig.from_pretrained(model_args.config_name, **config_kwargs)
@@ -364,7 +377,7 @@ def main():
"cache_dir": model_args.cache_dir,
"use_fast": model_args.use_fast_tokenizer,
"revision": model_args.model_revision,
"use_auth_token": True if model_args.use_auth_token else None,
"token": model_args.token,
}
if model_args.tokenizer_name:
tokenizer = AutoTokenizer.from_pretrained(model_args.tokenizer_name, **tokenizer_kwargs)
@@ -383,7 +396,7 @@ 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,
low_cpu_mem_usage=model_args.low_cpu_mem_usage,
)
else: