Fixed bug for utf-8 conversion

Project_Model/Libs/BPE/Classes/NanoSocratesBPE.py

@@ -90,7 +90,7 @@ class NanoSocratesBPE(Encoder):
 
     def encode(self, piece: str) -> list[int]:
 
-        current_piece = list(map(ord, piece))
+        current_piece = list(piece.encode("utf-8"))
         new_piece = self.__round_encode(current_piece)
 
         while len(current_piece) != len(new_piece):
@@ -128,7 +128,7 @@ class NanoSocratesBPE(Encoder):
 
         return NEW_PIECE
 
-    # TODO: decode
+    # TODO: Remake decode to take a list of token IDs
     def decode(self, token_id: int) -> str:
 
         token_stack: list[int] = [token_id]