diff --git a/convert-llama-7b-pth-to-gguf.py b/convert-llama-7b-pth-to-gguf.py
index d76350356..96d2e0800 100644
--- a/convert-llama-7b-pth-to-gguf.py
+++ b/convert-llama-7b-pth-to-gguf.py
@@ -110,8 +110,9 @@ gguf_writer.add_layer_norm_rms_eps(llm_arch, hparams["rms_norm_eps"])
 
 print("gguf: get tokenizer metadata")
 
-tokens: List[str] = []
+tokens: List[bytes] = []
 scores: List[float] = []
+toktypes: List[int] = []
 
 if Path(dir_model + "/tokenizer.model").is_file():
     # vocab type sentencepiece
@@ -121,26 +122,31 @@ if Path(dir_model + "/tokenizer.model").is_file():
 
     for i in range(tokenizer.vocab_size()):
         text: bytes
-        if tokenizer.is_unknown(i):
-            text = " \u2047 ".encode("utf-8")
-        elif tokenizer.is_control(i):
-            text = b""
-        if tokenizer.is_byte(i):
-            piece = tokenizer.id_to_piece(i)
-            if len(piece) != 6:
-                raise Exception(f"Invalid token: {piece}")
-            byte_value = int(piece[3:-1], 16)
-            text = struct.pack("B", byte_value)
-        else:
-            text = tokenizer.id_to_piece(i).replace("\u2581", " ").encode("utf-8")
-        score: float = tokenizer.get_score(i)
+        score: float
+
+        piece = tokenizer.id_to_piece(i)
+        text  = piece.encode("utf-8")
+        score = tokenizer.get_score(i)
+
+        toktype = 1 # defualt to normal token type
+        if tokenizer.is_unknown(i): toktype = 2
+        if tokenizer.is_control(i): toktype = 3
+ 
+        # TODO: How to determinate if a token is user defined?
+        # ref: https://github.com/google/sentencepiece/blob/master/src/sentencepiece_model.proto
+        # if tokenizer.is_user_defined(i): toktype = 4
+
+        if tokenizer.is_unused(i):  toktype = 5
+        if tokenizer.is_byte(i):    toktype = 6
 
         tokens.append(text)
         scores.append(score)
+        toktypes.append(toktype)
 
     gguf_writer.add_tokenizer_model("llama")
     gguf_writer.add_token_list(tokens)
     gguf_writer.add_token_scores(scores)
+    gguf_writer.add_token_types(toktypes)
 
 if Path(dir_model + "/tokenizer.json").is_file():
     with open(dir_model + "/tokenizer.json", "r", encoding="utf-8") as f: