Awni Hannun
@awnihannun
Machine Learning Research @Apple
ID:245262377
https://awnihannun.com/ 31-01-2011 08:05:27
1,7K Tweets
16,5K Followers
247 Following
Fine-tuning the latest Google Gemma model locally using MLX
Just a reminder of the power and hackability of Apple MLX πͺ
Great job Morning Coder π₯
Eric Hartford MLX
2bit: huggingface.co/mlx-community/β¦
4bit: huggingface.co/mlx-community/β¦
8bit: huggingface.co/mlx-community/β¦
Cool feature of the latest MLX:
Most MLX ops can take input arrays from your (second π) favorite ML framework.
All thanks to the multi-framework array support in Wenzel Jakob's Nanobind.
β
οΈ Tests passing for the Microsoft BitNet 1.58Bit LLM MLX implementation on Apple Silicon
This model from Microsoft is well suited to edge devices (e.g. iPad/iPhone/Macbook) since it uses 7x less memory and 71x less energy than LLaMA
h/t Awni Hannun Kyβ¨ Gomβ¨z (U/ACC) (HIRING) Prince Canuma
Cool new repo: faster-nougat
An MLX implementation of AI at Meta's Nougat for OCR-based RAG.
Code: github.com/zhuzilin/fasteβ¦
5x faster on an M1 pro than the baseline, no magic, just MLX:
MLX: Today I had to do some speech-to-text from English and Italian, I tried lightning-whisper-mlx and...
It is SUPER FAST! π₯
M3 Max 40GPU: 10.5 min audio in 6 seconds! π
Amazing work Mustafa Aljadery π
And thanks as always to Awni Hannun for MLX powering so many great
`mlx-embedding-models` update!
- now supports Nomic-BERT models thanks to a contribution from Zach Nussbaum!
- fixed a bug with mean-pooling
- has supported SPLADE for a while, i just forgot to tweet about it
pip install mlx-embedding-models
pypi.org/project/mlx-emβ¦