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

convert : fix required parameters in convert-llama-ggmlv3-to-gguf

Browse source
This commit is contained in:
Cebtenzzre 2023-08-30 15:45:38 -04:00
parent a09b674a98
commit 68738ff55a
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
convert-llama-ggmlv3-to-gguf.py
View file

@ -307,8 +307,8 @@ def handle_metadata(cfg, hp):
def handle_args(): def handle_args():
parser = argparse.ArgumentParser(description = 'Convert GGMLv3 models to GGUF') parser = argparse.ArgumentParser(description = 'Convert GGMLv3 models to GGUF')
parser.add_argument('--input', '-i', type = Path, help = 'Input GGMLv3 filename') parser.add_argument('--input', '-i', type = Path, required = True, help = 'Input GGMLv3 filename')
parser.add_argument('--output', '-o', type = Path, help ='Output GGUF filename') parser.add_argument('--output', '-o', type = Path, required = True, help ='Output GGUF filename')
parser.add_argument('--name', help = 'Set model name') parser.add_argument('--name', help = 'Set model name')
parser.add_argument('--desc', help = 'Set model description') parser.add_argument('--desc', help = 'Set model description')
parser.add_argument('--gqa', type = int, default = 1, help = 'grouped-query attention factor (use 8 for LLaMA2 70B)') parser.add_argument('--gqa', type = int, default = 1, help = 'grouped-query attention factor (use 8 for LLaMA2 70B)')