update example.

README.md

@@ -63,14 +63,13 @@ model_name = 'Intel/neural-chat-7b-v3-1'
 model = transformers.AutoModelForCausalLM.from_pretrained(model_name)
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
 
-
 def generate_response(system_input, user_input):
-    
+
     # Format the input using the provided template
     prompt = f"### System:\n{system_input}\n### User:\n{user_input}\n### Assistant:\n"
 
     # Tokenize and encode the prompt
-    inputs = tokenizer.encode(prompt, return_tensors="pt")
+    inputs = tokenizer.encode(prompt, return_tensors="pt", add_special_tokens=False)
 
     # Generate a response
     outputs = model.generate(inputs, max_length=1000, num_return_sequences=1)
@@ -81,10 +80,27 @@ def generate_response(system_input, user_input):
 
 
 # Example usage
-system_input = "You are a chatbot developed by Intel. Please answer all questions to the best of your ability."
-user_input = "How does the neural-chat-7b-v3-1 model work?"
+system_input = "You are a math expert assistant. Your mission is to help users understand and solve various math problems. You should provide step-by-step solutions, explain reasonings and give the correct answer."
+user_input = "calculate 100 + 520 + 60"
 response = generate_response(system_input, user_input)
 print(response)
+
+# expected response
+"""
+To calculate the sum of 100, 520, and 60, we will follow these steps:
+
+1. Add the first two numbers: 100 + 520
+2. Add the result from step 1 to the third number: (100 + 520) + 60
+
+Step 1: Add 100 and 520
+100 + 520 = 620
+
+Step 2: Add the result from step 1 to the third number (60)
+(620) + 60 = 680
+
+So, the sum of 100, 520, and 60 is 680.
+"""
+
 ```
 
 ## Ethical Considerations and Limitations