Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-29 07:34:18 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix outfile

Browse Source
This commit is contained in:
ngxson 2024-07-08 22:05:35 +02:00
parent 802565ca43
commit 95b3eb057b
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
convert_lora_to_gguf.py
View File

@ -31,7 +31,7 @@ def parse_args() -> argparse.Namespace:
description="Convert a huggingface PEFT LoRA adapter to a GGML compatible file") description="Convert a huggingface PEFT LoRA adapter to a GGML compatible file")
parser.add_argument( parser.add_argument(
"--outfile", type=Path, "--outfile", type=Path,
help="path to write to; default: based on input.", help="path to write to; default: based on input. {ftype} will be replaced by the outtype.",
) )
parser.add_argument( parser.add_argument(
"--outtype", type=str, choices=["f32", "f16", "bf16", "q8_0"], default="f16", "--outtype", type=str, choices=["f32", "f16", "bf16", "q8_0"], default="f16",
@ -77,7 +77,7 @@ if __name__ == '__main__':
fname_out = args.outfile fname_out = args.outfile
else: else:
# output in the same directory as the model by default # output in the same directory as the model by default
fname_out = dir_lora / 'ggml-lora.gguf' fname_out = dir_lora / 'ggml-lora-{ftype}.gguf'
if os.path.exists(input_model): if os.path.exists(input_model):
lora_model = torch.load(input_model, map_location="cpu") lora_model = torch.load(input_model, map_location="cpu")