diff --git a/README.md b/README.md
index 1a7ee616..bc7b3c4b 100644
--- a/README.md
+++ b/README.md
@@ -368,8 +368,7 @@ python src/export_model.py \
     --template default \
     --finetuning_type lora \
     --checkpoint_dir path_to_checkpoint \
-    --export_dir path_to_export \
-    --fp16
+    --export_dir path_to_export
 ```
 
 ### API Demo
diff --git a/README_zh.md b/README_zh.md
index 6a893084..c0722d5c 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -367,8 +367,7 @@ python src/export_model.py \
     --template default \
     --finetuning_type lora \
     --checkpoint_dir path_to_checkpoint \
-    --output_dir path_to_export \
-    --fp16
+    --export_dir path_to_export
 ```
 
 ### API 服务
diff --git a/src/llmtuner/tuner/core/loader.py b/src/llmtuner/tuner/core/loader.py
index 8f35183c..ef0e5d01 100644
--- a/src/llmtuner/tuner/core/loader.py
+++ b/src/llmtuner/tuner/core/loader.py
@@ -240,4 +240,7 @@ def load_model_and_tokenizer(
         trainable_params, all_param, 100 * trainable_params / all_param
     ))
 
+    if not is_trainable:
+        logger.info("This IS expected that the trainable params is 0 if you are using model for inference only.")
+
     return model, tokenizer