diff --git a/README.md b/README.md
index fcd839e..a7c50fa 100644
--- a/README.md
+++ b/README.md
@@ -48,14 +48,17 @@ We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and
 
 
 ## How to use
-Cloning the repo may be inefficient, and thus you can manually download the GGUF file that you need or use `huggingface-cli` (`pip install huggingface_hub`) as shown below:
-```shell
-huggingface-cli download Qwen/Qwen1.5-32B-Chat-GGUF qwen1_5-32b-chat-q5_k_m.gguf --local-dir . --local-dir-use-symlinks False
+Cloning the repo may be inefficient, and thus you can manually download the GGUF file that you need or use `modelscope` (`pip install modelscope`) as shown below:
+```python
+from modelscope.hub.file_download import model_file_download
+model_dir = model_file_download(model_id='qwen/Qwen1.5-32B-Chat-GGUF',file_path='qwen1_5-32b-chat-q5_k_m.gguf',revision='master',cache_dir='/mnt/workspace/')
 ```
 
-We demonstrate how to use `llama.cpp` to run Qwen1.5:
+We demonstrate how to install and use `llama.cpp` to run Qwen1.5:
 ```shell
-./main -m qwen1_5-32b-chat-q5_k_m.gguf -n 512 --color -i -cml -f prompts/chat-with-qwen.txt
+git clone https://github.com/ggerganov/llama.cpp.git
+cd llama.cpp
+make -j && ./main -m /mnt/workspace/qwen/Qwen1.5-32B-Chat-GGUF/qwen1_5-32b-chat-q5_k_m.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e
 ```