tristan/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show stats 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.I64: (1, 8),
GGMLQuantizationType.F64: (1, 8),
GGMLQuantizationType.IQ1_M: (256, QK_K // 8 + QK_K // 16 + QK_K // 32),
}