mirror of
https://git.adityakumar.xyz/llama.cpp.git
synced 2024-09-07 22:40:40 +00:00
convert.py : add missing abstract methods for quantized data (#2491)
This commit is contained in:
parent
f514d1b306
commit
2e8265ae17
|
@ -465,6 +465,13 @@ class GGMLQuantizedTensor(Tensor):
|
|||
def permute(self, n_head: int, n_kv_head: Optional[int] = None) -> 'GGMLQuantizedTensor':
|
||||
return GGMLQuantizedTensor(permute(self.ndarray, n_head, n_kv_head), self.shape, self.data_type)
|
||||
|
||||
def permute_part(self, n_part: int, n_head: int) -> 'UnquantizedTensor':
|
||||
r = self.ndarray.shape[0] // 3
|
||||
return UnquantizedTensor(permute(self.ndarray[r * n_part : r * n_part + r, ...], n_head))
|
||||
|
||||
def part(self, n_part: int) -> 'UnquantizedTensor':
|
||||
r = self.ndarray.shape[0] // 3
|
||||
return UnquantizedTensor(self.ndarray[r * n_part : r * n_part + r, ...])
|
||||
|
||||
GGMLCompatibleTensor = Union[UnquantizedTensor, GGMLQuantizedTensor]
|
||||
|
||||
|
|
Loading…
Reference in a new issue