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

35
examples/flax/summarization/run_summarization_flax.py
View File

@@ -24,6 +24,7 @@ import math
import os
import sys
import time
import warnings
from dataclasses import asdict, dataclass, field
from enum import Enum
from functools import partial
@@ -188,15 +189,21 @@ 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
@@ -417,6 +424,12 @@ 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="flax")
@@ -475,7 +488,7 @@ 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,
)
else:
data_files = {}
@@ -492,7 +505,7 @@ 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.
@@ -503,13 +516,13 @@ 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]()
@@ -520,14 +533,14 @@ 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(
@@ -541,7 +554,7 @@ 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 = FlaxAutoModelForSeq2SeqLM.from_config(