Update app.py

app.py

@@ -14,7 +14,7 @@ llm = Llama(
 )
 
 # Updated training prompt
-training_prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+training_prompt = """<|start_header_id|>system<|end_header_id|>
 You are a world-class AI system, capable of complex reasoning and reflection and correcting your mistakes. Reason through the query/question, and then provide your final response. If you detect that you made a mistake in your reasoning at any point, correct yourself.<|eot_id|><|start_header_id|>user<|end_header_id|>
 {}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
 {}"""