MLX code snippet

README.md

@@ -17,6 +17,28 @@ Phi-2 is a Transformer with **2.7 billion** parameters. It was trained using the
 
 Our model hasn't been fine-tuned through reinforcement learning from human feedback. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
 
+This repository contains the Phi-2 weights in `npz` format suitable for use with Apple's MLX framework.
+
+## Use with MLX
+
+```bash
+pip install mlx
+pip install transformers huggingface_hub hf_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-use-symlinks False --local-dir phi-2 mlx-community/phi-2
+
+# The phi2 example script currently requires the weights to be in the current dir
+ln -s phi-2/weights.npz .
+
+# Run example
+python mlx-examples/phi2/phi2.py --prompt "My name is"
+```
+
+The rest of the model card was copied from [the original Phi-2 repository](https://huggingface.co/microsoft/phi-2).
+
 ## Intended Uses
 
 Phi-2 is intended for research purposes only. Given the nature of the training data, the Phi-2 model is best suited for prompts using the QA format, the chat format, and the code format.