How to use sugatoray/mlx-alphamonarch-7b-q4bits with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download sugatoray/mlx-alphamonarch-7b-q4bits --local-dir mlx-alphamonarch-7b-q4bits
https://huggingface.co/sugatoray/mlx-alphamonarch-7b-q4bits/resolve/main/tokenizer.json
hf download hf://sugatoray/mlx-alphamonarch-7b-q4bits/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/sugatoray/mlx-alphamonarch-7b-q4bits/resolve/main/tokenizer.json
