Update README.md

README.md

@@ -26,4 +26,12 @@ inputs = inputs.to("cuda")
 generate_ids = model.generate(**inputs)
 output = tokenizer.batch_decode(generate_ids)[0]
 print(output)
-```
+```
+
+You could also alternatively launch a CLI demo by using the script in https://github.com/hiyouga/LLaMA-Efficient-Tuning
+```bash
+python src/cli_demo.py \
+    --model_name_or_path baichuan-inc/baichuan-7B \
+    --checkpoint_dir hiyouga/baichuan-7b-sft \
+    --prompt_template ziya
+```