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/token-classification/run_ner.py

@@ -95,6 +95,16 @@ 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."},
@@ -362,6 +372,7 @@ 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_name_or_path = model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path
@@ -372,6 +383,7 @@ def main():
             use_fast=True,
             revision=model_args.model_revision,
             token=model_args.token,
+            trust_remote_code=model_args.trust_remote_code,
             add_prefix_space=True,
         )
     else:
@@ -381,6 +393,7 @@ def main():
             use_fast=True,
             revision=model_args.model_revision,
             token=model_args.token,
+            trust_remote_code=model_args.trust_remote_code,
         )
 
     model = AutoModelForTokenClassification.from_pretrained(
@@ -390,6 +403,7 @@ 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/token-classification/run_ner_no_trainer.py

@@ -210,6 +210,16 @@ 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,
@@ -388,9 +398,13 @@ def main():
     # In distributed training, the .from_pretrained methods guarantee that only one local process can concurrently
     # download model & vocab.
     if args.config_name:
-        config = AutoConfig.from_pretrained(args.config_name, num_labels=num_labels)
+        config = AutoConfig.from_pretrained(
+            args.config_name, num_labels=num_labels, trust_remote_code=args.trust_remote_code
+        )
     elif args.model_name_or_path:
-        config = AutoConfig.from_pretrained(args.model_name_or_path, num_labels=num_labels)
+        config = AutoConfig.from_pretrained(
+            args.model_name_or_path, num_labels=num_labels, trust_remote_code=args.trust_remote_code
+        )
     else:
         config = CONFIG_MAPPING[args.model_type]()
         logger.warning("You are instantiating a new config instance from scratch.")
@@ -403,9 +417,13 @@ def main():
         )
 
     if config.model_type in {"bloom", "gpt2", "roberta"}:
-        tokenizer = AutoTokenizer.from_pretrained(tokenizer_name_or_path, use_fast=True, add_prefix_space=True)
+        tokenizer = AutoTokenizer.from_pretrained(
+            tokenizer_name_or_path, use_fast=True, add_prefix_space=True, trust_remote_code=args.trust_remote_code
+        )
     else:
-        tokenizer = AutoTokenizer.from_pretrained(tokenizer_name_or_path, use_fast=True)
+        tokenizer = AutoTokenizer.from_pretrained(
+            tokenizer_name_or_path, use_fast=True, trust_remote_code=args.trust_remote_code
+        )
 
     if args.model_name_or_path:
         model = AutoModelForTokenClassification.from_pretrained(
@@ -413,10 +431,11 @@ def main():
             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,
         )
     else:
         logger.info("Training new model from scratch")
-        model = AutoModelForTokenClassification.from_config(config)
+        model = AutoModelForTokenClassification.from_config(config, trust_remote_code=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.