thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

convert : allow quantizing lora again (#17453)

Browse source
This commit is contained in:
Sigbjørn Skjæret 2025-11-24 15:50:55 +01:00 • committed by GitHub
parent b8372eecd9
commit b61de2b2df
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert_lora_to_gguf.py
View file

@ -242,7 +242,7 @@ def parse_args() -> argparse.Namespace:
help="path to write to; default: based on input. {ftype} will be replaced by the outtype.",
)
parser.add_argument(
"--outtype", type=str, choices=["f32", "f16", "bf16", "q8_0", "auto"], default="f16",
"--outtype", type=str, choices=["f32", "f16", "bf16", "q8_0", "auto"], default="f32",
help="output format - use f32 for float32, f16 for float16, bf16 for bfloat16, q8_0 for Q8_0, auto for the highest-fidelity 16-bit float type depending on the first loaded tensor type",
)
parser.add_argument(