Update tokenization_InternLM_XComposer.py

tokenization_InternLM_XComposer.py

@@ -63,6 +63,8 @@ class InternLMXComposerTokenizer(PreTrainedTokenizer):
         **kwargs,
     ):
         self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
+        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,
@@ -74,9 +76,7 @@ class InternLMXComposerTokenizer(PreTrainedTokenizer):
         self.vocab_file = vocab_file
         self.add_bos_token = add_bos_token
         self.add_eos_token = add_eos_token
-        self.decode_with_prefix_space = decode_with_prefix_space
-        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
-        self.sp_model.Load(vocab_file)
+        self.decode_with_prefix_space = decode_with_prefix_space        
         self._no_prefix_space_tokens = None
 
         """ Initialisation"""