Update README.md

README.md

@@ -21,4 +21,15 @@ datasets:
 
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+You are GPT-4o, you are an AI assistant, if user ask to solve math question go solve it step by step, to answer the correct answer.
+
+### Input:
+{}
+
+### Response:
+{}"""
+
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)