Instructions to use typealias/llm-compiler-7b-ftd-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use typealias/llm-compiler-7b-ftd-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir llm-compiler-7b-ftd-mlx-4bit typealias/llm-compiler-7b-ftd-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- Xet hash:
- 1df6207aeb3dc0ed3b8e28d59434550ca6311491af5a6bf147dc5250802bc33a
- Size of remote file:
- 500 kB
- SHA256:
- 7d77173a958615d2779fe7b6771a8e310f6f448715f56038a24c1641f9359a67
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.