update tokenizer.py

tokenizer.py

@@ -327,6 +327,9 @@ class PhobertTokenizer(PreTrainedTokenizer):
         """
         Loads a pre-existing dictionary from a text file and adds its symbols to this instance.
         """
+
+        for word in LATEX_VOC:
+            self.encoder[word] = len(self.encoder)
         if isinstance(f, str):
             try:
                 with open(f, "r", encoding="utf-8") as fd:
@@ -345,5 +348,3 @@ class PhobertTokenizer(PreTrainedTokenizer):
                 raise ValueError("Incorrect dictionary format, expected '<token> <cnt>'")
             word = line[:idx]
             self.encoder[word] = len(self.encoder)
-        for word in LATEX_VOC:
-            self.encoder[word] = len(self.encoder)