Update README.md

README.md

@@ -54,7 +54,7 @@ tokenized_chat = tokenizer.apply_chat_template(
 ).to(model.device)
 generated_ids = model.generate(tokenized_chat, max_new_tokens=512)
 generated_ids = [
-    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(tokenized_chat, generated_ids)
 ]
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(response)