try

modeling.py

@@ -773,7 +773,7 @@ class STLTokenizer(PreTrainedTokenizer):
     """
 
     def __init__(self, vocab_path: str, unk_token: str = "unk", pad_token: str = "pad", 
-                 bos_token: str = "/s", eos_token: str = "s", model_max_length = 512):
+                 bos_token: str = "/s", eos_token: str = "s", model_max_length = 512, *args, **kwargs):
         """
         Initializes the STLTokenizer with a given vocabulary and special tokens.
 
@@ -791,6 +791,8 @@ class STLTokenizer(PreTrainedTokenizer):
         self.eos_token = eos_token
         self.model_max_length = model_max_length
         self.id_to_token = {v: k for k, v in self.vocab.items()}  # Reverse mapping
+        super().__init__(unk_token=unk_token, pad_token=pad_token, bos_token=bos_token, eos_token=eos_token, 
+                         model_max_length=model_max_length, *args, **kwargs)
 
     @property
     def vocab_size(self) -> int: