Update README.md

README.md

@@ -36,10 +36,8 @@ tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
 model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)
 
 # Format the input as a chat template
-user_turn_1 = "In one season a flower blooms three times. In one year, there is one blooming season. How many times do two flowers bloom in two years? Please include your logic."
-assistant_turn_1 = "In one season, a flower blooms three times. In one year, there is one blooming season. Therefore, in two years, there are two blooming seasons. Since each flower blooms three times in one season, in two blooming seasons, each flower will bloom six times. Since there are two flowers, the total number of times they will bloom in two years is 12."
-user_turn_2 = "How many times do the two flowers blossom in three years?"
-sample = [{'role': 'user', 'content': user_turn_1}, {'role': 'assistant', 'content': assistant_turn_1}, {'role': 'user', 'content': user_turn_2}]
+prompt = "What factors contributed to the fall of the Roman Empire?"
+sample = [{'role': 'user', 'content': prompt}]
 chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)
 
 # Tokenize input and generate output