mlx.core.load#

mlx.core.load(file: str, /, format: Optional[str] = None, return_metadata: bool = False, *, stream: Union[None, Stream, Device] = None) → Union[array, Dict[str, array]]#

Load array(s) from a binary file.

The supported formats are .npy, .npz, .safetensors, and .gguf.

Parameters:

  • file (file, str) – File in which the array is saved.

  • format (str, optional) – Format of the file. If None, the format is inferred from the file extension. Supported formats: npy, npz, and safetensors. Default: None.

  • return_metadata (bool, optional) – Load the metadata for formats which support matadata. The metadata will be returned as an additional dictionary.

Returns:

A single array if loading from a .npy file or a dict mapping names to arrays if loading from a .npz or .safetensors file. If return_metadata` is ``True an additional dictionary of metadata will be returned.

Return type:

result (array, dict)

Warning

When loading unsupported quantization formats from GGUF, tensors will automatically cast to mx.float16