root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

gguf-dump : support i-quants (#5841)

Browse Source 
Co-authored-by: Black_Fox <radekliska@gmail.com>
This commit is contained in:
Nindaleth 2024-03-03 09:43:42 +01:00 committed by GitHub
parent de9692a7d2
commit 87c2e8b279
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 44 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
gguf-py/gguf/constants.py
View File

@ -618,6 +618,14 @@ class GGMLQuantizationType(IntEnum):
Q5_K = 13
Q6_K = 14
Q8_K = 15
IQ2_XXS = 16
IQ2_XS = 17
IQ3_XXS = 18
IQ1_S = 19
IQ4_NL = 20
IQ3_S = 21
IQ2_S = 22
IQ4_XS = 23
class GGUFEndian(IntEnum):
@ -676,6 +684,14 @@ GGML_QUANT_SIZES = {
GGMLQuantizationType.Q5_K: (256, 2 + 2 + QK_K // 2 + QK_K // 8 + 12),
GGMLQuantizationType.Q6_K: (256, 2 + QK_K // 2 + QK_K // 4 + QK_K // 16),
GGMLQuantizationType.Q8_K: (256, 4 + QK_K + QK_K // 8),
GGMLQuantizationType.IQ2_XXS: (256, 2 + QK_K // 4),
GGMLQuantizationType.IQ2_XS: (256, 2 + QK_K // 4 + QK_K // 32),
GGMLQuantizationType.IQ3_XXS: (256, 2 + QK_K // 4 + QK_K // 8),
GGMLQuantizationType.IQ1_S: (256, 2 + QK_K // 8 + QK_K // 16),
GGMLQuantizationType.IQ4_NL: (32, 2 + 16),
GGMLQuantizationType.IQ3_S: (256, 2 + QK_K // 4 + QK_K // 8 + QK_K // 32 + 4),
GGMLQuantizationType.IQ2_S: (256, 2 + QK_K // 4 + QK_K // 16),
GGMLQuantizationType.IQ4_XS: (256, 2 + 2 + QK_K // 2 + QK_K // 64),
}