diff --git a/onnxruntime_extensions/_hf_cvt.py b/onnxruntime_extensions/_hf_cvt.py
index e379c9834..6113e86a9 100644
--- a/onnxruntime_extensions/_hf_cvt.py
+++ b/onnxruntime_extensions/_hf_cvt.py
@@ -43,10 +43,11 @@ def convert_json_vocab(hf_tokenizer):
                 f"{hf_tokenizer.__name__}: vocab_files_names is not found")
 
         tokenizer_file = filenames["tokenizer_file"]
-        if (hf_tokenizer.vocab_file is None) or (not os.path.exists(hf_tokenizer.vocab_file)):
+        vocab_file = getattr(hf_tokenizer, "vocab_file", None)
+        if (vocab_file is None) or (not os.path.exists(vocab_file)):
             model_dir = hf_tokenizer.name_or_path
         else:
-            model_dir = os.path.dirname(hf_tokenizer.vocab_file)
+            model_dir = os.path.dirname(vocab_file)
         tokenizer_json = json.load(
             open(os.path.join(model_dir, tokenizer_file), "r", encoding="utf-8"))
         # get vocab object from json file
@@ -181,6 +182,8 @@ def spm_decoder(self, **kwargs):
                                          'BpeDecoder',      HFTokenizerConverter.bpe_decoder, None),
     "CodeGenTokenizer":     TokenOpParam('GPT2Tokenizer',   HFTokenizerConverter.bpe_tokenizer,
                                          'BpeDecoder',      HFTokenizerConverter.bpe_decoder, None),
+    "GPTNeoXTokenizer":     TokenOpParam('GPT2Tokenizer',   HFTokenizerConverter.bpe_tokenizer,
+                                         'BpeDecoder',      HFTokenizerConverter.bpe_decoder, None),
     "CLIPTokenizer":        TokenOpParam('CLIPTokenizer',   HFTokenizerConverter.clip_tokenizer,
                                          'BpeDecoder',      HFTokenizerConverter.bpe_decoder, None),
     "RobertaTokenizer":     TokenOpParam('RobertaTokenizer',        HFTokenizerConverter.roberta_tokenizer,