Fix for tokenization

configuration_mixformer_sequential.py

@@ -41,7 +41,7 @@ class MixFormerSequentialConfig(PretrainedConfig):
         pad_vocab_size_multiple: Optional[int] = 64,
         **kwargs
     ) -> None:
-        self.vocab_size = int(math.ceil(vocab_size / pad_vocab_size_multiple) * pad_vocab_size_multiple)
+        self.vocab_size = vocab_size
         self.n_positions = n_positions
         self.n_embd = n_embd
         self.n_layer = n_layer