haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

convert.py : add missing abstract methods for quantized data (#2491)

Browse source
This commit is contained in:
Keiichi Tabata 2023-08-06 15:34:05 +09:00 committed by GitHub
parent f514d1b306
commit 2e8265ae17
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
convert.py
View file

@ -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]