Update app.py

app.py

@@ -95,7 +95,7 @@ def stream_chat(
     )
 
     with torch.no_grad():
-        thread = Thread(target=model.generate, kwargs=gen_kwargs)
+        thread = Thread(target=model.generate, kwargs=generate_kwargs)
         thread.start()
         
     buffer = ""
@@ -130,7 +130,7 @@ with gr.Blocks(css=CSS, theme="soft") as demo:
                 maximum=8192,
                 step=1,
                 value=1024,
-                label="Max Length",
+                label="Max new tokens",
                 render=False,
             ),
             gr.Slider(