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/flax/language-modeling/run_clm_flax.py

@@ -185,6 +185,16 @@ 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
@@ -477,12 +487,14 @@ def main():
             model_args.config_name,
             cache_dir=model_args.cache_dir,
             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,
             cache_dir=model_args.cache_dir,
             token=model_args.token,
+            trust_remote_code=model_args.trust_remote_code,
         )
     else:
         config = CONFIG_MAPPING[model_args.model_type]()
@@ -494,6 +506,7 @@ def main():
             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(
@@ -501,6 +514,7 @@ def main():
             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(
@@ -515,12 +529,14 @@ def main():
             seed=training_args.seed,
             dtype=getattr(jnp, model_args.dtype),
             token=model_args.token,
+            trust_remote_code=model_args.trust_remote_code,
         )
     else:
         model = FlaxAutoModelForCausalLM.from_config(
             config,
             seed=training_args.seed,
             dtype=getattr(jnp, model_args.dtype),
+            trust_remote_code=model_args.trust_remote_code,
         )
 
     # Preprocessing the datasets.

examples/flax/language-modeling/run_mlm_flax.py

@@ -190,6 +190,16 @@ 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
@@ -509,12 +519,14 @@ def main():
             model_args.config_name,
             cache_dir=model_args.cache_dir,
             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,
             cache_dir=model_args.cache_dir,
             token=model_args.token,
+            trust_remote_code=model_args.trust_remote_code,
         )
     else:
         config = CONFIG_MAPPING[model_args.model_type]()
@@ -526,6 +538,7 @@ def main():
             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(
@@ -533,6 +546,7 @@ def main():
             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(
@@ -652,12 +666,14 @@ def main():
             seed=training_args.seed,
             dtype=getattr(jnp, model_args.dtype),
             token=model_args.token,
+            trust_remote_code=model_args.trust_remote_code,
         )
     else:
         model = FlaxAutoModelForMaskedLM.from_config(
             config,
             seed=training_args.seed,
             dtype=getattr(jnp, model_args.dtype),
+            trust_remote_code=model_args.trust_remote_code,
         )
 
     if training_args.gradient_checkpointing: