add trust_remote_code argument (#2715)

fastchat/train/train.py

@@ -36,6 +36,12 @@
 @dataclass
 class ModelArguments:
     model_name_or_path: Optional[str] = field(default="facebook/opt-125m")
+    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"
+        },
+    )
     padding_side: str = field(
         default="right", metadata={"help": "The padding side in tokenizer"}
     )
@@ -260,6 +266,7 @@ def train():
     config = transformers.AutoConfig.from_pretrained(
         model_args.model_name_or_path,
         cache_dir=training_args.cache_dir,
+        trust_remote_code=model_args.trust_remote_code,
     )
     orig_ctx_len = getattr(config, "max_position_embeddings", None)
     if orig_ctx_len and training_args.model_max_length > orig_ctx_len:
@@ -272,13 +279,15 @@ def train():
         model_args.model_name_or_path,
         config=config,
         cache_dir=training_args.cache_dir,
+        trust_remote_code=model_args.trust_remote_code,
     )
     tokenizer = transformers.AutoTokenizer.from_pretrained(
         model_args.model_name_or_path,
         cache_dir=training_args.cache_dir,
         model_max_length=training_args.model_max_length,
         padding_side=model_args.padding_side,
         use_fast=False,
+        trust_remote_code=model_args.trust_remote_code,
     )
 
     if tokenizer.pad_token != tokenizer.unk_token: