def gaudi_validate_environment()

in optimum/habana/quantizers/bitsandbytes.py [0:0]

• 36 lines of code
• 14 McCabe index (conditional complexity)

def gaudi_validate_environment(self, *args, **kwargs):
    """
    Copied from https://github.com/huggingface/transformers/blob/5523e38b553ff6c46b04d2376870fcd842feeecc/src/transformers/quantizers/quantizer_bnb_4bit.py#L68
    Only difference is deletion of bitsandbytes version checks
    """
    if not is_accelerate_available():
        raise ImportError(
            f"Using `bitsandbytes` 4-bit quantization requires Accelerate: `pip install 'accelerate>={ACCELERATE_MIN_VERSION}'`"
        )
    if not gaudi_is_bitsandbytes_available():
        raise ImportError(
            "Using `bitsandbytes` 4-bit quantization requires the latest version of bitsandbytes: `pip install -U bitsandbytes`"
        )

    bnb_multibackend_is_enabled = is_bitsandbytes_multi_backend_available()
    gaudi_validate_bnb_backend_availability(raise_exception=True)

    if kwargs.get("from_tf", False) or kwargs.get("from_flax", False):
        raise ValueError(
            "Converting into 4-bit or 8-bit weights from tf/flax weights is currently not supported, please make"
            " sure the weights are in PyTorch format."
        )

    device_map = kwargs.get("device_map", None)
    if (
        device_map is not None
        and isinstance(device_map, dict)
        and not self.quantization_config.llm_int8_enable_fp32_cpu_offload
    ):
        device_map_without_lm_head = {
            key: device_map[key] for key in device_map.keys() if key not in self.modules_to_not_convert
        }
        if set(device_map.values()) == {"cpu"} and bnb_multibackend_is_enabled:
            pass
        elif "cpu" in device_map_without_lm_head.values() or "disk" in device_map_without_lm_head.values():
            raise ValueError(
                "Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit the "
                "quantized model. If you want to dispatch the model on the CPU or the disk while keeping these modules "
                "in 32-bit, you need to set `load_in_8bit_fp32_cpu_offload=True` and pass a custom `device_map` to "
                "`from_pretrained`. Check "
                "https://huggingface.co/docs/transformers/main/en/main_classes/quantization#offload-between-cpu-and-gpu "
                "for more details. "
            )