diff --git a/README.md b/README.md
index a7c50fa..8e88ef2 100644
--- a/README.md
+++ b/README.md
@@ -33,6 +33,7 @@ To demonstrate their model quality, we follow [`llama.cpp`](https://github.com/g
 |4B      | 13.20   | 13.21   | 13.28   | 13.24   | 13.27   | 13.61   | 13.44   | 13.67   | 15.65   |
 |7B      | 14.21   | 14.24   | 14.35   | 14.32   | 14.12   | 14.35   | 14.47   | 15.11   | 16.57   |
 |14B     | 10.91   | 10.91   | 10.93   | 10.98   | 10.88   | 10.92   | 10.92   | 11.24   | 12.27   |
+|32B     | 8.87    | 8.89    | 8.91    | 8.94    | 8.93    | 8.96    | 9.17    | 9.14    | 10.51   |
 |72B     | 7.97    | 7.99    | 7.99    | 7.99    | 8.01    | 8.00    | 8.01    | 8.06    | 8.63    |
 
 ## Model Details
@@ -48,17 +49,14 @@ 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 `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/')
+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
 ```
 
-We demonstrate how to install and use `llama.cpp` to run Qwen1.5:
+We demonstrate how to use `llama.cpp` to run Qwen1.5:
 ```shell
-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
+./main -m qwen1_5-32b-chat-q5_k_m.gguf -n 512 --color -i -cml -f prompts/chat-with-qwen.txt
 ```