Instructions to use assassindesign/Hy-MT2-1.8B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use assassindesign/Hy-MT2-1.8B-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Hy-MT2-1.8B-MLX-4bit assassindesign/Hy-MT2-1.8B-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
- Xet hash:
- 15735f041aabe477a3deb662ed2a5aaf5f943d430030205b8d67afe9a157c95a
- Size of remote file:
- 1.01 GB
- SHA256:
- a9cecbc77050b86b2fa3df3a8941d34ed3585cdbcce07bd64b3da289d50537c6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.