Update README.md

README.md

@@ -64,8 +64,22 @@ model = AutoModelForCausalLM.from_pretrained(
 model.generation_config.pad_token_id = tokenizer.eos_token_id
 
 # Inference simple as transformers library
-prompt = "Describe basics of DNNs quantization."
-inputs = tokenizer(prompt, return_tensors="pt")
+messages = [
+                {
+                    "role": "system",
+                    "content": "You are a search bot, answer on user text queries."
+                },
+                {
+                    "role": "user",
+                    "content": "Describe basics of DNNs quantization."
+                }
+            ]
+
+chat_prompt = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, tokenize=False
+)
+
+inputs = tokenizer(chat_prompt, return_tensors="pt")
 inputs.to(device)
 
 with torch.inference_mode: