modified the gpu , to stay within the limit

app.py

@@ -153,7 +153,7 @@ def generate_response_for_chunk(chunk, history, temperature, max_new_tokens):
     
     return "".join(outputs)
 
-@spaces.GPU(duration=120)
+@spaces.GPU(duration=110)
 def chat_llama3_8b(message: str, history: list, temperature: float, max_new_tokens: int):
     """
     Generate a streaming response using the llama3-8b model with chunking.