How to use voxmenthe/SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download voxmenthe/SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized --local-dir SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized
https://huggingface.co/voxmenthe/SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized/resolve/refs%2Fpr%2F2/tokenizer.json
hf download hf://voxmenthe/SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized@refs/pr/2/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/voxmenthe/SFR-Iterative-DPO-LLaMA-3-8B-R-unquantized/resolve/refs%2Fpr%2F2/tokenizer.json
