Update README.md

README.md

@@ -60,8 +60,19 @@ model, tokenizer = FastLanguageModel.from_pretrained(
     dtype = dtype,
     load_in_4bit = load_in_4bit,
 )
-
 FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+
+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:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
 inputs = tokenizer(
 [
     alpaca_prompt.format(