Instructions to use beezu/Anubis-70B-v1-MLX-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use beezu/Anubis-70B-v1-MLX-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Anubis-70B-v1-MLX-4Bit beezu/Anubis-70B-v1-MLX-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
- Xet hash:
- 7225607987ff5fbc2091e0a5364ee3587f101076041020fa01bb275a6499191b
- Size of remote file:
- 5.27 GB
- SHA256:
- 8e23162d68023dc12c1e1f9bba4f10abcf28f0d326f01e2954a531d33767552d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.