Prompting

pip install -U mlx-lm
python -m mlx_lm.generate --model chenhunghan/TAIDE-LX-7B-Chat-mlx-4bit --prompt 'TAIDE可以吃嗎？'

Convert

python -m mlx_lm.convert --hf-path taide/TAIDE-LX-7B-Chat -q

Safetensors

Model size

1.28B params

Tensor type

FP16

U32

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.