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

gguf-py: Add IQ1_M to GGML_QUANT_SIZES

Browse source
This commit is contained in:
Piotr Myśliński 2024-04-19 06:59:07 +02:00
parent bca40e9814
commit 5622e3aa22
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -859,6 +859,7 @@ GGML_QUANT_SIZES = {
GGMLQuantizationType.I32: (1, 4), GGMLQuantizationType.I32: (1, 4),
GGMLQuantizationType.I64: (1, 8), GGMLQuantizationType.I64: (1, 8),
GGMLQuantizationType.F64: (1, 8), GGMLQuantizationType.F64: (1, 8),
GGMLQuantizationType.IQ1_M: (256, QK_K // 8 + QK_K // 16 + QK_K // 32),
} }