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

Allow trust_remote_code in example scripts (#25248)

Browse Source 
* pytorch examples

* pytorch mim no trainer

* cookiecutter

* flax examples

* missed line in pytorch run_glue

* tensorflow examples

* tensorflow run_clip

* tensorflow run_mlm

* tensorflow run_ner

* tensorflow run_clm

* pytorch example from_configs

* pytorch no trainer examples

* Revert "tensorflow run_clip"

This reverts commit 261f86ac1f1c9e05dd3fd0291e1a1f8e573781d5.

* fix: duplicated argument
This commit is contained in:
Jackmin801
2023-08-07 22:32:25 +08:00
committed by GitHub
parent 65001cb1c8
commit 145109382a
49 changed files with 790 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
examples/tensorflow/language-modeling/run_clm.py
View File

@@ -128,6 +128,16 @@ 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."
)
},
)
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):
@@ -366,17 +376,26 @@ def main():
# In distributed training, the .from_pretrained methods guarantee that only one local process can concurrently
# download model & vocab.
if model_args.config_name:
config = AutoConfig.from_pretrained(model_args.config_name)
config = AutoConfig.from_pretrained(
model_args.config_name,
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)
config = AutoConfig.from_pretrained(
model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
)
else:
config = CONFIG_MAPPING[model_args.model_type]()
logger.warning("You are instantiating a new config instance from scratch.")
if model_args.tokenizer_name:
tokenizer = AutoTokenizer.from_pretrained(model_args.tokenizer_name)
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name, 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)
tokenizer = AutoTokenizer.from_pretrained(
model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
)
else:
raise ValueError(
"You are instantiating a new tokenizer from scratch. This is not supported by this script."
@@ -479,12 +498,16 @@ def main():
with training_args.strategy.scope():
# region Prepare model
if checkpoint is not None:
model = TFAutoModelForCausalLM.from_pretrained(checkpoint, config=config)
model = TFAutoModelForCausalLM.from_pretrained(
checkpoint, config=config, 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)
model = TFAutoModelForCausalLM.from_pretrained(
model_args.model_name_or_path, config=config, trust_remote_code=model_args.trust_remote_code
)
else:
logger.info("Training new model from scratch")
model = TFAutoModelForCausalLM.from_config(config)
model = TFAutoModelForCausalLM.from_config(config, 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.

36
examples/tensorflow/language-modeling/run_mlm.py
View File

@@ -126,6 +126,16 @@ 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."
)
},
)
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):
@@ -348,19 +358,25 @@ 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)
config = AutoConfig.from_pretrained(checkpoint, trust_remote_code=model_args.trust_remote_code)
elif model_args.config_name:
config = AutoConfig.from_pretrained(model_args.config_name)
config = AutoConfig.from_pretrained(model_args.config_name, 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)
config = AutoConfig.from_pretrained(
model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
)
else:
config = CONFIG_MAPPING[model_args.model_type]()
logger.warning("You are instantiating a new config instance from scratch.")
if model_args.tokenizer_name:
tokenizer = AutoTokenizer.from_pretrained(model_args.tokenizer_name)
tokenizer = AutoTokenizer.from_pretrained(
model_args.tokenizer_name, 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)
tokenizer = AutoTokenizer.from_pretrained(
model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
)
else:
raise ValueError(
"You are instantiating a new tokenizer from scratch. This is not supported by this script."
@@ -495,12 +511,16 @@ def main():
with training_args.strategy.scope():
# region Prepare model
if checkpoint is not None:
model = TFAutoModelForMaskedLM.from_pretrained(checkpoint, config=config)
model = TFAutoModelForMaskedLM.from_pretrained(
checkpoint, config=config, 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)
model = TFAutoModelForMaskedLM.from_pretrained(
model_args.model_name_or_path, config=config, trust_remote_code=model_args.trust_remote_code
)
else:
logger.info("Training new model from scratch")
model = TFAutoModelForMaskedLM.from_config(config)
model = TFAutoModelForMaskedLM.from_config(config, 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.