Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 13:58:46 +01:00
Code Issues Packages Projects Releases Wiki Activity

add 4_0 to default outfile namestr dict (#1031)

Browse Source 
this came up when trying to convert the gpt4all-lora-unfiltered-quantized.bin file
This commit is contained in:
Cameron 2023-04-17 11:26:23 -07:00 committed by GitHub
parent 315a95a4d3
commit 4ad73137a1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
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]
@ -1108,7 +1109,7 @@ def main(args_in: Optional[List[str]] = None) -> None:
parser.add_argument("--dump", action="store_true", help="don't convert, just show what's in the model")
parser.add_argument("--dump-single", action="store_true", help="don't convert, just show what's in a single model file")
parser.add_argument("--vocab-only", action="store_true", help="extract only the vocab")
parser.add_argument("--outtype", choices=["f32", "f16", "q4_1"], help="output format (default: based on input)")
parser.add_argument("--outtype", choices=["f32", "f16", "q4_1", "q4_0"], help="output format (default: based on input)")
parser.add_argument("--vocab-dir", type=Path, help="directory containing tokenizer.model, if separate from model file")
parser.add_argument("--outfile", type=Path, help="path to write to; default: based on input")
parser.add_argument("model", type=Path, help="directory containing model file, or model file itself (*.pth, *.pt, *.bin)")