https://github.com/uogbuji/mlx-notes

Shared personal notes created while working with the Apple MLX machine learning framework
https://github.com/uogbuji/mlx-notes

apple articles documentation jupyter-notebooks large-language-models llm machine-learning mlx python

Last synced: 8 days ago
JSON representation

Shared personal notes created while working with the Apple MLX machine learning framework

• Host: GitHub
• URL: https://github.com/uogbuji/mlx-notes
• Owner: uogbuji
• License: cc-by-4.0
• Created: 2024-03-20T05:49:30.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-06-21T14:56:25.000Z (5 months ago)
• Last Synced: 2024-06-22T09:33:30.012Z (5 months ago)
• Topics: apple, articles, documentation, jupyter-notebooks, large-language-models, llm, machine-learning, mlx, python
• Language: Jupyter Notebook
• Homepage: https://ucheog.carrd.co/
• Size: 13.8 MB
• Stars: 13
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Notes on the Apple MLX machine learning framework

## Apple MLX for AI/Large Language Models—Day One

  

  

  Rendered markdown


  LinkedIn version


  Jupyter notebook

  

## Converting models from Hugging Face to MLX format, and sharing

  

  

  Rendered markdown


  LinkedIn version


  Jupyter notebook

  

## Retrieval augmentation with MLX: A bag full of RAG, part 1

  

  

  Rendered markdown


  LinkedIn version


  Jupyter notebook

  

## Retrieval augmentation with MLX: A bag full of RAG, part 2

  

  

  Rendered markdown


  LinkedIn version


  Jupyter notebook

  

  

# More (up to date) MLX resources

* [MLX home page](https://github.com/ml-explore/mlx)

* [Hugging Face MLX community](https://huggingface.co/mlx-community)

* [Using MLX at Hugging Face](https://huggingface.co/docs/hub/en/mlx)

* [MLX Text-completion Finetuning Notebook](https://github.com/mark-lord/MLX-text-completion-notebook)

* [MLX Tuning Fork—Framework for parameterized large language model (Q)LoRa fine-tuning using mlx, mlx_lm, and OgbujiPT. Architecture for systematic running of easily parameterized fine-tunes](https://github.com/chimezie/mlx-tuning-fork)

# A few general notes

* For the many chat formats already charted out in llama.cpp, see the `@register_chat_format` decorated functions in [llama_chat_format.py](https://github.com/abetlen/llama-cpp-python/blob/main/llama_cpp/llama_chat_format.py)

## To do, or figure out

* [any grammar/ebnf support a la llama.cpp](https://christophergs.com/blog/running-open-source-llms-in-python#grammar)?

* Alternate LLM sampling methods

* Steering vectors

# Syncing articles to notebooks

Use [Jupytext](https://jupytext.readthedocs.io/en/latest/) to convert the `.md` articles to `.ipynb` notebooks:

```sh

jupytext --to ipynb 2024/MLX-day-one.md

```

May have to convert cells using plain `pip` to use `%pip` instead. It also doesn't seem to check the format metadata, so you might need to convert non-Python cells back to Markdown by hand.

# License

Shield: [![CC BY 4.0][cc-by-shield]][cc-by]

This work is licensed under a

[Creative Commons Attribution 4.0 International License][cc-by].

[![CC BY 4.0][cc-by-image]][cc-by]

[cc-by]: http://creativecommons.org/licenses/by/4.0/

[cc-by-image]: https://i.creativecommons.org/l/by/4.0/88x31.png

[cc-by-shield]: https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg

See also: https://github.com/santisoler/cc-licenses?tab=readme-ov-file#cc-attribution-40-international