# MLX Examples

This repo contains a variety of standalone examples using the [MLX
framework](https://github.com/ml-explore/mlx).

The [MNIST](mnist) example is a good starting point to learn how to use MLX.

Some more useful examples include:

- [Transformer language model](transformer_lm) training.
- Large scale text generation with [LLaMA](llama), [Mistral](mistral) or [Phi](phi2).  
- Mixture-of-experts (MoE) language model with [Mixtral 8x7B](mixtral)
- Parameter efficient fine-tuning with [LoRA](lora).
- Generating images with [Stable Diffusion](stable_diffusion).
- Speech recognition with [OpenAI's Whisper](whisper).
- Bidirectional language understanding with [BERT](bert)
- Semi-supervised learning on graph-structured data with [GCN](gcn).

Note: You can now directly download a few converted checkpoints from the [MLX Community](https://huggingface.co/mlx-community) organisation on Hugging Face.

## Contributing 

We are grateful for all of [our
contributors](ACKNOWLEDGMENTS.md#Individual-Contributors). If you contribute
to MLX Examples and wish to be acknowledged, please add your name to to the list in your
pull request.

## Citing MLX Examples

The MLX software suite was initially developed with equal contribution by Awni
Hannun, Jagrit Digani, Angelos Katharopoulos, and Ronan Collobert. If you find
MLX Examples useful in your research and wish to cite it, please use the following
BibTex entry:

```
@software{mlx2023,
  author = {Awni Hannun and Jagrit Digani and Angelos Katharopoulos and Ronan Collobert},
  title = {{MLX}: Efficient and flexible machine learning on Apple silicon},
  url = {https://github.com/ml-explore},
  version = {0.0},
  year = {2023},
}
```