nwpie/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2026-02-05 13:53:23 +02:00
Code Issues Packages Projects Releases Wiki Activity

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
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
convert_hf_to_gguf.py
View File

@@ -565,7 +565,7 @@ class ModelBase:
gguf.MODEL_TENSOR.ALTUP_PREDICT_COEF,
)
)
or not new_name.endswith(".weight")
or new_name[-7:] not in (".weight", ".lora_a", ".lora_b")
):
data_qtype = gguf.GGMLQuantizationType.F32

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(