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

convert-hf : support q8_0 conversion

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-05-10 14:47:28 -04:00
parent 5a419926b0
commit d7e199e444
5 changed files with 157 additions and 57 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -2,5 +2,6 @@ from .constants import *
from .lazy import *
from .gguf_reader import *
from .gguf_writer import *
from .quants import *
from .tensor_mapping import *
from .vocab import *