Instructions to use mzbac/mlx-yayi2-30b-guanaco-4-bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mzbac/mlx-yayi2-30b-guanaco-4-bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir mlx-yayi2-30b-guanaco-4-bit mzbac/mlx-yayi2-30b-guanaco-4-bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Run it using the MlX framework. For more details, click here.
python yayi.py --model-path <path_to_mlx_model> --prompt "### Human: 你好\n### Assistant:"
Prompt template:
### Human: {prompt}
### Assistant:
- Downloads last month
- 25
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support