Allow trust_remote_code in example scripts (#25248)

* 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

View File

@@ -198,6 +198,16 @@ 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."
)
},
)
@dataclass
@@ -489,17 +499,20 @@ def main():
seed=training_args.seed,
dtype=getattr(jnp, model_args.dtype),
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
image_processor = AutoImageProcessor.from_pretrained(
model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
token=model_args.token,
trust_remote_code=model_args.trust_remote_code,
)
tokenizer = AutoTokenizer.from_pretrained(
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,
)
tokenizer.pad_token = tokenizer.convert_ids_to_tokens(model.config.pad_token_id)