Update app.py

Using the smaller 0.6B model to because of resource allocation issues

app.py

@@ -130,7 +130,7 @@ class ModelWrapper:
             input_length = len(message)
             return output_text[input_length:] if len(output_text) > input_length else "No response generated."
 
-MODEL_NAME = "Qwen/Qwen3-8B"
+MODEL_NAME = "Qwen/Qwen3-0.6B"
 model = ModelWrapper(MODEL_NAME)
 
 # — Gradio inference function —