Update app.py

app.py

@@ -45,7 +45,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
 terminators = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>")]
 
 
-@spaces.GPU(duration=120)
+@spaces.GPU
 def chat_llama3_8b(
     message: str, history: list, temperature: float, max_new_tokens: int
 ) -> Generator[str, None, None]:
@@ -130,9 +130,6 @@ with gr.Blocks(fill_height=True, css=css) as demo:
             ),
         ],
         examples=[
-            ["How to setup a human base on Mars? Give short answer."],
-            ["Explain theory of relativity to me like I’m 8 years old."],
-            ["What is 9,000 * 9,000?"],
             ["The detonative temperature of this polypropylene is 2000°F."],
             ["The preparation method according to claim 1, characterized in that the SO2 accounts for 30 wt% and the Fe2O3 accounts for 70 wt%."],
         ],