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

iq1_M: PR comments

Browse source
This commit is contained in:
Iwan Kawrakow 2024-03-26 15:46:11 +02:00
parent cdb2d65c8e
commit 6e4cef5d0c
2 changed files with 7 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

12
ggml.h
View file

@ -364,12 +364,12 @@ extern "C" {
GGML_TYPE_IQ3_S = 21, GGML_TYPE_IQ3_S = 21,
GGML_TYPE_IQ2_S = 22, GGML_TYPE_IQ2_S = 22,
GGML_TYPE_IQ4_XS = 23, GGML_TYPE_IQ4_XS = 23,
GGML_TYPE_IQ1_M = 24, GGML_TYPE_I8 = 24,
GGML_TYPE_I8 = 25, GGML_TYPE_I16 = 25,
GGML_TYPE_I16 = 26, GGML_TYPE_I32 = 26,
GGML_TYPE_I32 = 27, GGML_TYPE_I64 = 27,
GGML_TYPE_I64 = 28, GGML_TYPE_F64 = 28,
GGML_TYPE_F64 = 29, GGML_TYPE_IQ1_M = 29,
GGML_TYPE_COUNT, GGML_TYPE_COUNT,
}; };

1
gguf-py/gguf/constants.py
View file

@ -706,6 +706,7 @@ class GGMLQuantizationType(IntEnum):
I32 = 26 I32 = 26
I64 = 27 I64 = 27
F64 = 28 F64 = 28
IQ1_M = 29
class GGUFEndian(IntEnum): class GGUFEndian(IntEnum):