diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 82febc4b6..af7408be9 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -1236,6 +1236,7 @@ LlamaFileTypeMap: dict[LlamaFileType, GGMLQuantizationType] = { LlamaFileType.MOSTLY_Q4_0_8_8: GGMLQuantizationType.Q4_0_8_8, } + class GGUFEndian(IntEnum): LITTLE = 0 BIG = 1 diff --git a/gguf-py/gguf/quants.py b/gguf-py/gguf/quants.py index 3f0e58db1..abc621163 100644 --- a/gguf-py/gguf/quants.py +++ b/gguf-py/gguf/quants.py @@ -69,12 +69,12 @@ class __Quant(ABC): @classmethod @abstractmethod def quantize_blocks(cls, blocks: np.ndarray) -> np.ndarray: - raise NotImplemented + raise NotImplementedError @classmethod @abstractmethod def dequantize_blocks(cls, blocks: np.ndarray) -> np.ndarray: - raise NotImplemented + raise NotImplementedError @classmethod def quantize_rows(cls, rows: np.ndarray) -> np.ndarray: