Update README.md

README.md

@@ -96,9 +96,7 @@ You may also construct the pipeline from the loaded model and tokenizer yourself
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_name = "shashank-mugiwara/thor"  # either local folder or huggingface model name
-# Important: The prompt needs to be in the same format the model was trained with.
-# You can find an example prompt in the experiment logs.
-prompt = "<|prompt|>How are you?</s><|answer|>"
+prompt = "<|prompt|>What is thor service?</s><|answer|>"
 
 tokenizer = AutoTokenizer.from_pretrained(
     model_name,