Shell snippet for MLX (#2)

- Shell snippet for MLX (b31a554dd9607a5fa94d725f7d7b02510d934f49)

README.md

@@ -15,5 +15,22 @@ Llama 2 is a collection of pretrained and fine-tuned generative text models rang
 
 Weights have been converted to `float16` from the original `bfloat16` type, because `numpy` is not compatible with `bfloat16` out of the box.
 
+How to use with [MLX](https://github.com/ml-explore/mlx).
+
+```bash
+
+# Install mlx, mlx-examples, huggingface-cli
+pip install mlx
+pip install huggingface_hub huggingface_transfer
+git clone https://github.com/ml-explore/mlx-examples.git
+
+# Download model
+export HF_HUB_ENABLE_HF_TRANSFER=1
+huggingface-cli download --local-dir models --local-dir-use-symlinks False mlx-llama/Llama-2-7b-chat-mlx Llama-2-7b-chat-mlx
+
+# Run example
+python mlx-examples/llama/llama.py Llama-2-7b-chat-mlx/Llama-2-7b-chat.npz Llama-2-7b-chat-mlx/tokenizer.model "My name is "
+```
+
 Please, refer to the [original model card](https://huggingface.co/meta-llama/Llama-2-7b-chat/tree/main) for details on Llama 2.