Update README.md

README.md

@@ -42,7 +42,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config)
 
 question = "What color is the sky?"
-prompt = tokenizer.apply_chat_template([{"role": "user", "content": question}])
+prompt = tokenizer.apply_chat_template([{"role": "user", "content": question}], tokenize=False)
 inputs = tokenizer(prompt, return_tensors="pt")
 
 outputs = model.generate(**inputs, max_new_tokens=32)