How to use jesusoctavioas/gpt2-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download jesusoctavioas/gpt2-mlx-4Bit --local-dir gpt2-mlx-4Bit
https://huggingface.co/jesusoctavioas/gpt2-mlx-4Bit/resolve/main/tokenizer.json
hf download hf://jesusoctavioas/gpt2-mlx-4Bit/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/jesusoctavioas/gpt2-mlx-4Bit/resolve/main/tokenizer.json
