How to use willlordarm/Mistral-7B-Instruct-v0.3-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download willlordarm/Mistral-7B-Instruct-v0.3-mlx-4Bit --local-dir Mistral-7B-Instruct-v0.3-mlx-4Bit
https://huggingface.co/willlordarm/Mistral-7B-Instruct-v0.3-mlx-4Bit/resolve/main/tokenizer.json
hf download hf://willlordarm/Mistral-7B-Instruct-v0.3-mlx-4Bit/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/willlordarm/Mistral-7B-Instruct-v0.3-mlx-4Bit/resolve/main/tokenizer.json
