diff --git a/README.md b/README.md
index 2cc80e6..c6d9d97 100644
--- a/README.md
+++ b/README.md
@@ -40,14 +40,14 @@ Check out our [llama.cpp documentation](https://qwen.readthedocs.io/en/latest/ru
 We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and install it following the official guide. We follow the latest version of llama.cpp. 
 In the following demonstration, we assume that you are running commands under the repository `llama.cpp`.
 
-Since cloning the entire repo may be inefficient, you can manually download the GGUF file that you need or use `modelscope`:
+Since cloning the entire repo may be inefficient, you can manually download the GGUF file that you need or use `huggingface-cli`:
 1. Install
    ```shell
-   pip install -U modelscope
+   pip install -U huggingface_hub
    ```
 2. Download:
    ```shell
-   modelscope download --model=qwen/Qwen2.5-1.5B-Instruct-GGUF --local_dir . qwen2.5-1.5b-instruct-q5_k_m.gguf
+   huggingface-cli download Qwen/Qwen2.5-1.5B-Instruct-GGUF qwen2.5-1.5b-instruct-q5_k_m.gguf --local-dir . --local-dir-use-symlinks False
    ```
 
 For users, to achieve chatbot-like experience, it is recommended to commence in the conversation mode: