update(README): advise downloading files with `hf_transfer` enabled

README.md

@@ -37,10 +37,12 @@ Make sure to install release [b2684](https://github.com/ggerganov/llama.cpp/rele
 Download any of the available GGUF files. For example, using the Hugging Face Hub CLI:
 
 ```bash
+pip install huggingface_hub[hf_transfer]
+export HF_HUB_ENABLE_HF_TRANSFER=1
 huggingface-cli download stabilityai/stablelm-2-12b-chat-GGUF stablelm-2-12b-chat-Q5_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 
-Then run the model with the [main](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) program:
+Then run the model with the [llama.cpp `main`](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) program:
 
 ```bash
 ./main -m stablelm-2-12b-chat-Q5_K_M.gguf -p "<|im_start|>user {PROMPT} <|im_end|><|im_start|>assistant"