Update README.md

README.md

@@ -288,6 +288,17 @@ $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
 pip install llama-cpp-python
 ```
 
+#### Download the model into current directory
+
+```
+from huggingface_hub import hf_hub_download
+
+REPO_ID = "SalmanFaroz/Meta-Llama-3-8B-Instruct-GGUF"
+FILENAME = "Q4_K_M.gguf"
+
+hf_hub_download(repo_id=REPO_ID, filename=FILENAME,local_dir="./")
+```
+
 #### Simple llama-cpp-python example code
 
 ```python