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

examples/pytorch/text-classification/run_classification.py

@@ -243,6 +243,16 @@ 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."
+            )
+        },
+    )
     ignore_mismatched_sizes: bool = field(
         default=False,
         metadata={"help": "Will enable to load a pretrained model whose head dimensions are different."},
@@ -482,6 +492,7 @@ 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,
     )
 
     if is_regression:
@@ -500,6 +511,7 @@ def main():
         use_fast=model_args.use_fast_tokenizer,
         revision=model_args.model_revision,
         token=model_args.token,
+        trust_remote_code=model_args.trust_remote_code,
     )
     model = AutoModelForSequenceClassification.from_pretrained(
         model_args.model_name_or_path,
@@ -508,6 +520,7 @@ 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,
         ignore_mismatched_sizes=model_args.ignore_mismatched_sizes,
     )
 

examples/pytorch/text-classification/run_glue.py

@@ -204,6 +204,16 @@ 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."
+            )
+        },
+    )
     ignore_mismatched_sizes: bool = field(
         default=False,
         metadata={"help": "Will enable to load a pretrained model whose head dimensions are different."},
@@ -375,6 +385,7 @@ 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,
     )
     tokenizer = AutoTokenizer.from_pretrained(
         model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
@@ -382,6 +393,7 @@ def main():
         use_fast=model_args.use_fast_tokenizer,
         revision=model_args.model_revision,
         token=model_args.token,
+        trust_remote_code=model_args.trust_remote_code,
     )
     model = AutoModelForSequenceClassification.from_pretrained(
         model_args.model_name_or_path,
@@ -390,6 +402,7 @@ 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,
         ignore_mismatched_sizes=model_args.ignore_mismatched_sizes,
     )
 

examples/pytorch/text-classification/run_glue_no_trainer.py

@@ -156,6 +156,16 @@ def parse_args():
         "--hub_model_id", type=str, help="The name of the repository to keep in sync with the local `output_dir`."
     )
     parser.add_argument("--hub_token", type=str, help="The token to use to push to the Model Hub.")
+    parser.add_argument(
+        "--trust_remote_code",
+        type=bool,
+        default=False,
+        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."
+        ),
+    )
     parser.add_argument(
         "--checkpointing_steps",
         type=str,
@@ -309,13 +319,21 @@ def main():
     #
     # In distributed training, the .from_pretrained methods guarantee that only one local process can concurrently
     # download model & vocab.
-    config = AutoConfig.from_pretrained(args.model_name_or_path, num_labels=num_labels, finetuning_task=args.task_name)
-    tokenizer = AutoTokenizer.from_pretrained(args.model_name_or_path, use_fast=not args.use_slow_tokenizer)
+    config = AutoConfig.from_pretrained(
+        args.model_name_or_path,
+        num_labels=num_labels,
+        finetuning_task=args.task_name,
+        trust_remote_code=args.trust_remote_code,
+    )
+    tokenizer = AutoTokenizer.from_pretrained(
+        args.model_name_or_path, use_fast=not args.use_slow_tokenizer, trust_remote_code=args.trust_remote_code
+    )
     model = AutoModelForSequenceClassification.from_pretrained(
         args.model_name_or_path,
         from_tf=bool(".ckpt" in args.model_name_or_path),
         config=config,
         ignore_mismatched_sizes=args.ignore_mismatched_sizes,
+        trust_remote_code=args.trust_remote_code,
     )
 
     # Preprocessing the datasets

examples/pytorch/text-classification/run_xnli.py

@@ -168,6 +168,16 @@ 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."
+            )
+        },
+    )
     ignore_mismatched_sizes: bool = field(
         default=False,
         metadata={"help": "Will enable to load a pretrained model whose head dimensions are different."},
@@ -292,6 +302,7 @@ 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,
     )
     tokenizer = AutoTokenizer.from_pretrained(
         model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
@@ -300,6 +311,7 @@ def main():
         use_fast=model_args.use_fast_tokenizer,
         revision=model_args.model_revision,
         token=model_args.token,
+        trust_remote_code=model_args.trust_remote_code,
     )
     model = AutoModelForSequenceClassification.from_pretrained(
         model_args.model_name_or_path,
@@ -308,6 +320,7 @@ 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,
         ignore_mismatched_sizes=model_args.ignore_mismatched_sizes,
     )