import sys

# CUDA_DEVICE_ORDER=PCI_BUS_ID CUDA_VISIBLE_DEVICES=3 ~/llama.cpp/build/bin/llama-server \
#   -m /home/mshahidul/readctrl_model/translate_gemma/translategemma-27b-it-Q8_0.gguf \
#   --n-gpu-layers 999 \
#   --flash-attn on

from huggingface_hub import hf_hub_download


def main() -> int:
    try:
        hf_hub_download(
            repo_id="bullerwins/translategemma-27b-it-GGUF",
            filename="translategemma-27b-it-Q8_0.gguf",
            local_dir="/home/mshahidul/readctrl_model/translate_gemma",
            local_dir_use_symlinks=False,
        )
        return 0
    except ImportError:
        print("huggingface_hub not found. Install it and try again.", file=sys.stderr)
        return 1
    except Exception as exc:
        print(str(exc), file=sys.stderr)
        return 1


if __name__ == "__main__":
    raise SystemExit(main())