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

Fix missing usage of token (#25382)

Browse Source 
* add missing tokens

* fix

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar
2023-08-08 16:27:24 +02:00
committed by GitHub
parent 5bd8c011bb
commit 9c7b744795
6 changed files with 96 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
examples/tensorflow/contrastive-image-text/run_clip.py
View File

@@ -108,6 +108,16 @@ class ModelArguments:
"help": "The `use_auth_token` argument is deprecated and will be removed in v4.34. Please use `token`."
},
)
trust_remote_code: bool = field(
default=False,
metadata={
"help": (
"Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
"should only be set to `True` for repositories you trust and in which you have read the code, as it will"
"execute code present on the Hub on your local machine."
)
},
)
freeze_vision_model: bool = field(
default=False, metadata={"help": "Whether to freeze the vision model parameters or not."}
)
@@ -353,15 +363,27 @@ def main():
# 5. Load pretrained model, tokenizer, and image processor
if model_args.tokenizer_name:
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name, cache_dir=model_args.cache_dir, use_fast=model_args.use_fast_tokenizer
model_args.tokenizer_name,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
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
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
elif model_args.text_model_name_or_path:
tokenizer = AutoTokenizer.from_pretrained(
model_args.text_model_name_or_path, cache_dir=model_args.cache_dir, use_fast=model_args.use_fast_tokenizer
model_args.text_model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast_tokenizer,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
else:
raise ValueError(
@@ -376,6 +398,7 @@ def main():
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
with training_args.strategy.scope():
model = TFAutoModel.from_pretrained(
@@ -383,6 +406,7 @@ def main():
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
else:
# Load image_processor, in this script we only use this to get the mean and std for normalization.
@@ -391,6 +415,7 @@ def main():
cache_dir=model_args.cache_dir,
revision=model_args.model_revision,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
with training_args.strategy.scope():
model = TFVisionTextDualEncoderModel.from_vision_text_pretrained(
@@ -398,6 +423,7 @@ def main():
text_model_name_or_path=model_args.text_model_name_or_path,
cache_dir=model_args.cache_dir,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
config = model.config

18
examples/tensorflow/language-modeling/run_clm.py
View File

@@ -378,11 +378,12 @@ def main():
if model_args.config_name:
config = AutoConfig.from_pretrained(
model_args.config_name,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
elif model_args.model_name_or_path:
config = AutoConfig.from_pretrained(
model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
model_args.model_name_or_path, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
else:
config = CONFIG_MAPPING[model_args.model_type]()
@@ -390,11 +391,11 @@ def main():
if model_args.tokenizer_name:
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name, trust_remote_code=model_args.trust_remote_code
model_args.tokenizer_name, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
elif model_args.model_name_or_path:
tokenizer = AutoTokenizer.from_pretrained(
model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
model_args.model_name_or_path, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
else:
raise ValueError(
@@ -499,15 +500,20 @@ def main():
# region Prepare model
if checkpoint is not None:
model = TFAutoModelForCausalLM.from_pretrained(
checkpoint, config=config, trust_remote_code=model_args.trust_remote_code
checkpoint, config=config, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
elif model_args.model_name_or_path:
model = TFAutoModelForCausalLM.from_pretrained(
model_args.model_name_or_path, config=config, trust_remote_code=model_args.trust_remote_code
model_args.model_name_or_path,
config=config,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
else:
logger.info("Training new model from scratch")
model = TFAutoModelForCausalLM.from_config(config, trust_remote_code=model_args.trust_remote_code)
model = TFAutoModelForCausalLM.from_config(
config, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
# We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch
# on a small vocab and want a smaller embedding size, remove this test.

25
examples/tensorflow/language-modeling/run_mlm.py
View File

@@ -358,12 +358,16 @@ def main():
# In distributed training, the .from_pretrained methods guarantee that only one local process can concurrently
# download model & vocab.
if checkpoint is not None:
config = AutoConfig.from_pretrained(checkpoint, trust_remote_code=model_args.trust_remote_code)
config = AutoConfig.from_pretrained(
checkpoint, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
elif model_args.config_name:
config = AutoConfig.from_pretrained(model_args.config_name, trust_remote_code=model_args.trust_remote_code)
config = AutoConfig.from_pretrained(
model_args.config_name, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
elif model_args.model_name_or_path:
config = AutoConfig.from_pretrained(
model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
model_args.model_name_or_path, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
else:
config = CONFIG_MAPPING[model_args.model_type]()
@@ -371,11 +375,11 @@ def main():
if model_args.tokenizer_name:
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name, trust_remote_code=model_args.trust_remote_code
model_args.tokenizer_name, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
elif model_args.model_name_or_path:
tokenizer = AutoTokenizer.from_pretrained(
model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
model_args.model_name_or_path, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
else:
raise ValueError(
@@ -512,15 +516,20 @@ def main():
# region Prepare model
if checkpoint is not None:
model = TFAutoModelForMaskedLM.from_pretrained(
checkpoint, config=config, trust_remote_code=model_args.trust_remote_code
checkpoint, config=config, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
elif model_args.model_name_or_path:
model = TFAutoModelForMaskedLM.from_pretrained(
model_args.model_name_or_path, config=config, trust_remote_code=model_args.trust_remote_code
model_args.model_name_or_path,
config=config,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
else:
logger.info("Training new model from scratch")
model = TFAutoModelForMaskedLM.from_config(config, trust_remote_code=model_args.trust_remote_code)
model = TFAutoModelForMaskedLM.from_config(
config, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
# We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch
# on a small vocab and want a smaller embedding size, remove this test.

7
examples/tensorflow/token-classification/run_ner.py
View File

@@ -317,12 +317,14 @@ def main():
config = AutoConfig.from_pretrained(
model_args.config_name,
num_labels=num_labels,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
elif model_args.model_name_or_path:
config = AutoConfig.from_pretrained(
model_args.model_name_or_path,
num_labels=num_labels,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
else:
@@ -341,12 +343,14 @@ def main():
tokenizer_name_or_path,
use_fast=True,
add_prefix_space=True,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
else:
tokenizer = AutoTokenizer.from_pretrained(
tokenizer_name_or_path,
use_fast=True,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
# endregion
@@ -419,12 +423,13 @@ def main():
model = TFAutoModelForTokenClassification.from_pretrained(
model_args.model_name_or_path,
config=config,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
else:
logger.info("Training new model from scratch")
model = TFAutoModelForTokenClassification.from_config(
config, trust_remote_code=model_args.trust_remote_code
config, token=model_args.token, trust_remote_code=model_args.trust_remote_code
)
# We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch