Method to_ggml

tokenizer/convert/convert.py:610–611

(self)

        return UnquantizedTensor(self.ndarray.astype(dtype))

    def to_ggml(self) -> UnquantizedTensor:
        return self

    def permute_part(self, n_part: int, n_head: int, n_head_kv: int) -> UnquantizedTensor:
        r = self.ndarray.shape[0] // 3