Update app.py

app.py

@@ -8,8 +8,8 @@ model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
 pipeline = transformers.pipeline(
     "text-generation",
     model=model_id,
-    model_kwargs={"torch_dtype": torch.bfloat16 if torch.cuda.is_available() else torch.float32},
-    device_map="auto"
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
 )
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
@@ -45,7 +45,7 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
     return response_text, history
 
 # Define the Gradio interface
-demo = gr.ChatInterface(
+chatiface = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a pirate chatbot who always responds in pirate speak!", label="System message"),
@@ -55,6 +55,5 @@ demo = gr.ChatInterface(
     ]
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    chatiface.launch()