diff --git a/README.md b/README.md
index cdcb2046..36351a65 100644
--- a/README.md
+++ b/README.md
@@ -479,7 +479,9 @@ python src/export_model.py \
     --adapter_name_or_path path_to_checkpoint \
     --template default \
     --finetuning_type lora \
-    --export_dir path_to_export
+    --export_dir path_to_export \
+    --export_size 2 \
+    --export_legacy_format False
 ```
 
 > [!WARNING]
diff --git a/README_zh.md b/README_zh.md
index 2adef5af..a5e13e3b 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -479,7 +479,9 @@ python src/export_model.py \
     --adapter_name_or_path path_to_checkpoint \
     --template default \
     --finetuning_type lora \
-    --export_dir path_to_export
+    --export_dir path_to_export \
+    --export_size 2 \
+    --export_legacy_format False
 ```
 
 > [!WARNING]
diff --git a/src/llmtuner/hparams/model_args.py b/src/llmtuner/hparams/model_args.py
index 3f415bee..36ff1e3f 100644
--- a/src/llmtuner/hparams/model_args.py
+++ b/src/llmtuner/hparams/model_args.py
@@ -102,7 +102,7 @@ class ModelArguments:
         default=1024,
         metadata={"help": "The maximum length of the model inputs used for quantization."}
     )
-    export_lecacy_format: Optional[bool] = field(
+    export_legacy_format: Optional[bool] = field(
         default=False,
         metadata={"help": "Whether or not to save the `.bin` files instead of `.safetensors`."}
     )
diff --git a/src/llmtuner/train/tuner.py b/src/llmtuner/train/tuner.py
index 033c20f5..63813edd 100644
--- a/src/llmtuner/train/tuner.py
+++ b/src/llmtuner/train/tuner.py
@@ -50,7 +50,7 @@ def export_model(args: Optional[Dict[str, Any]] = None):
     model.save_pretrained(
         save_directory=model_args.export_dir,
         max_shard_size="{}GB".format(model_args.export_size),
-        safe_serialization=(not model_args.export_lecacy_format)
+        safe_serialization=(not model_args.export_legacy_format)
     )
 
     try: