Update boomer_code_tokenizer.py

boomer_code_tokenizer.py

@@ -63,10 +63,10 @@ class BoomerCodeTokenizer(PreTrainedTokenizer):
 
     def __init__(self, vocab_file, bos_token=None, eos_token='<|endoftext|>', unk_token='<|unk|>', pad_token='<|pad|>', sep_token=None, sp_model_kwargs: Optional[Dict[str, Any]]=None, **kwargs) -> None:
         self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
-        super().__init__(bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, pad_token=pad_token, sep_token=sep_token, sp_model_kwargs=self.sp_model_kwargs, **kwargs)
         self.vocab_file = vocab_file
         self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
         self.sp_model.Load(vocab_file)
+        super().__init__(bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, pad_token=pad_token, sep_token=sep_token, sp_model_kwargs=self.sp_model_kwargs, **kwargs)
         
         print(self.sp_model)