Use both eos tokens

app.py

@@ -84,6 +84,7 @@ def chat_llama3_8b(message: str,
         max_new_tokens=max_new_tokens,
         do_sample=True,
         temperature=temperature,
+        eos_token_id=[128001, 128009],
     )
     # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
     if temperature == 0: