Update app.py

app.py

@@ -31,7 +31,7 @@ def generate(prompt, history):
 
     formatted_prompt = format_prompt(prompt, history)
 
-    response = inference_client.text_generation(formatted_prompt, **kwargs, stream=True, details=True, return_full_text=True)
+    response = inference_client.text_generation(formatted_prompt, **kwargs, stream=True, details=True, return_full_text=False)
     output = ""
 
     for chunk in response: