tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)

Browse Source
This commit is contained in:
pmysl
2024-04-21 14:49:30 +02:00
committed by GitHub
parent e8d35f47cb
commit c1386c936e
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

@ -872,6 +872,7 @@ 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),
} }