specify Qwen3-VL-4B-Instruct

README.md

@@ -20,7 +20,7 @@ license: mit
 
 ## Model Description
 
-**LabVLA** is the first vision–language–action (VLA) model designed for scientific laboratory environments. It combines a **Qwen3-VL-4B** vision–language backbone with a **DiT flow-matching action expert**, trained with the π0.5 recipe to enable real-time robot control in lab settings.
+**LabVLA** is the first vision–language–action (VLA) model designed for scientific laboratory environments. It combines a **Qwen3-VL-4B-Instruct** vision–language backbone with a **DiT flow-matching action expert**, trained with the π0.5 recipe to enable real-time robot control in lab settings.
 
 ## How to Use