Update README.md

README.md

@@ -23,5 +23,20 @@ pip install mlx-lm
 from mlx_lm import load, generate
 
 model, tokenizer = load("mlx-community/Qwen1.5-1.8B-Chat-4bit")
-response = generate(model, tokenizer, prompt="hello", verbose=True)
+
+prompt = "hello"
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+response = generate(model, tokenizer, prompt=text, verbose=True, max_tokens=200)
+
 ```