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

convert.py: We can't currently support Q8_0 on big endian.

Browse source
This commit is contained in:
KerfuffleV2 2023-11-10 05:50:15 -07:00
parent 0b0e726b2d
commit 960f912a14
1 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
convert.py
View file

@ -1112,11 +1112,15 @@ def do_dump_model(model_plus: ModelPlus) -> None:
def main(args_in: list[str] | None = None) -> None: def main(args_in: list[str] | None = None) -> None:
output_choices = ["f32", "f16"]
if np.uint32(1) == np.uint32(1).newbyteorder("<"):
# We currently only support Q8_0 output on little endian systems.
output_choices.append("q8_0")
parser = argparse.ArgumentParser(description="Convert a LLaMa model to a GGML compatible file") parser = argparse.ArgumentParser(description="Convert a LLaMa model to a GGML compatible file")
parser.add_argument("--dump", action="store_true", help="don't convert, just show what's in the model") 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("--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("--vocab-only", action="store_true", help="extract only the vocab")
parser.add_argument("--outtype", choices=["f32", "f16", "q8_0"], help="output format - note: q8_0 may be very slow (default: f16 or f32 based on input)") parser.add_argument("--outtype", choices=output_choices, help="output format - note: q8_0 may be very slow (default: f16 or f32 based on input)")
parser.add_argument("--vocab-dir", type=Path, help="directory containing tokenizer.model, if separate from model file") 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("--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)") parser.add_argument("model", type=Path, help="directory containing model file, or model file itself (*.pth, *.pt, *.bin)")