diff --git a/examples/lm_finetuning/pregenerate_training_data.py b/examples/lm_finetuning/pregenerate_training_data.py
index 6cb8954465..8bed1e54d4 100644
--- a/examples/lm_finetuning/pregenerate_training_data.py
+++ b/examples/lm_finetuning/pregenerate_training_data.py
@@ -270,7 +270,7 @@ def main():
     parser.add_argument("--output_dir", type=Path, required=True)
     parser.add_argument("--bert_model", type=str, required=True,
                         choices=["bert-base-uncased", "bert-large-uncased", "bert-base-cased",
-                                 "bert-base-multilingual", "bert-base-chinese"])
+                                 "bert-base-multilingual-uncased", "bert-base-chinese", "bert-base-multilingual-cased"])
     parser.add_argument("--do_lower_case", action="store_true")
     parser.add_argument("--do_whole_word_mask", action="store_true",
                         help="Whether to use whole word masking rather than per-WordPiece masking.")