docs: add llama download command (#460)

Co-authored-by: Terry Kong <terryk@nvidia.com>

docs/user-guide/dpo.rst

@@ -49,7 +49,11 @@ To start, we must first get a pretrained model to align. There are two models we
     .. tab-item:: LLaMa3 8B
         :sync: key2
 
-        #. Download the `Llama 3 8B LLM model and tokenizer <https://huggingface.co/meta-llama/Meta-Llama-3-8B>`__ into the models folder.
+        #. Download the `Llama 3 8B LLM model and tokenizer <https://huggingface.co/meta-llama/Meta-Llama-3-8B>`__ into the models folder. You can use the Hugging Face CLI for this:
+            .. code-block:: bash
+
+               huggingface-cli download meta-llama/Meta-Llama-3-8B --local-dir /path/to/llama
+
         #. Convert the LLaMa3 LLM into ``.nemo`` format.
             .. code-block:: bash