diff --git a/convert.py b/convert.py
old mode 100755
new mode 100644
index 4ba36f2801891..0428c229f6ddb
--- a/convert.py
+++ b/convert.py
@@ -741,6 +741,8 @@ def add_meta_vocab(self, vocab: Vocab) -> None:
         tokens = []
         scores = []
         toktypes = []
+        # NOTE: `all_tokens` returns the the base vocabulary and added tokens
+        # TODO: add special tokens?
         for text, score, toktype in vocab.all_tokens():
             tokens.append(text)
             scores.append(score)
@@ -751,8 +753,6 @@ def add_meta_vocab(self, vocab: Vocab) -> None:
         self.gguf.add_token_scores(scores)
         self.gguf.add_token_types(toktypes)
 
-        # TODO: added / special tokens
-
     def add_tensor_info(self, name: str, tensor: LazyTensor) -> None:
         n_elements = 1
         for dim in tensor.shape:
diff --git a/tests/test-tokenizer-1.cpp b/tests/test-tokenizer-1.cpp
index a8a7e88988260..d8db7cd96eaa4 100644
--- a/tests/test-tokenizer-1.cpp
+++ b/tests/test-tokenizer-1.cpp
@@ -87,8 +87,8 @@ int main(int argc, char **argv) {
                 return 2;
             }
         } else {
-            // TODO: needs access to token types
-            if (0 <= i && i < 259) {
+            llama_token_type type = llama_token_get_type(ctx, i);
+            if (type == LLAMA_TOKEN_TYPE_UNKNOWN || type == LLAMA_TOKEN_TYPE_CONTROL || type == LLAMA_TOKEN_TYPE_BYTE) {
                 fprintf(stderr, "%s : info: token %d is string %s and bpe returns tokens %s\n",
                     __func__, i, llama_token_to_str(ctx, i).c_str(), unescape_whitespace(ctx, tokens).c_str());
             } else {