fix the usage

README.md

@@ -40,14 +40,14 @@ model.to(device)
 
 # 2. prepare inputs
 text = "知識蒸留について簡単に教えてください。"
-messages = [
-    {"role": "system", "content": "あなたは誠実で優秀な日本人のアシスタントです。"},
-    {"role": "user", "content": text},
-]
-inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
+messages = [{"role": "user", "content": text}]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
 
 # 3. generate
-output_ids = model.generate(**inputs.to(device))
+output_ids = model.generate(
+    inputs.to(device),
+    max_new_tokens=1024,
+)
 output_ids = output_ids[:, inputs.input_ids.shape[1] :]
 generated_text = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0]
 print(generated_text)