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

add 4_0 to default outfile namestr dict

Browse source 
This came up when trying to convert the gpt4all-lora-unfiltered-quantized.bin file
This commit is contained in:
Cammy 2023-04-17 09:11:14 -07:00
parent 315a95a4d3
commit 74e28db50f
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
convert.py
View file

@ -1085,6 +1085,7 @@ def default_outfile(model_paths: List[Path], params: Params) -> Path:
namestr = {
GGMLFileType.AllF32: "f32",
GGMLFileType.MostlyF16: "f16",
GGMLFileType.MostlyQ4_0: "q4_0",
GGMLFileType.MostlyQ4_1: "q4_1",
GGMLFileType.PerLayerIsQ4_1: "q4_1",
}[params.file_type]