We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent e2b1a5e commit 255c220Copy full SHA for 255c220
gguf-py/gguf/constants.py
@@ -1320,6 +1320,7 @@ class GGMLQuantizationType(IntEnum):
1320
IQ2_KT = 153
1321
IQ3_KT = 154
1322
IQ4_KT = 155
1323
+ IQ3_KS = 156
1324
Q4_0_R8 = 202
1325
Q5_0_R4 = 206
1326
Q8_0_R8 = 208
@@ -1535,6 +1536,7 @@ def get_type(val: Any) -> GGUFValueType:
1535
1536
GGMLQuantizationType.IQ2_KT : ( 256, 68),
1537
GGMLQuantizationType.IQ3_KT : ( 256, 100),
1538
GGMLQuantizationType.IQ4_KT : ( 256, 128),
1539
+ GGMLQuantizationType.IQ3_KS : ( 256, 102),
1540
GGMLQuantizationType.Q4_0_R8 : ( 32, 18),
1541
GGMLQuantizationType.Q5_0_R4 : ( 32, 22),
1542
GGMLQuantizationType.Q8_0_R8 : ( 32, 34),
0 commit comments