Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 05:48:47 +01:00
Code Issues Packages Projects Releases Wiki Activity

convert.py: also look for plain model.safetensors (#4043)

Browse Source 
* add safetensors to convert.py help message

* Check for single-file safetensors model

* Update convert.py "model" option help message

* revert convert.py help message change
This commit is contained in:
afrideva 2023-11-13 17:03:40 -08:00 committed by GitHub
parent bd90eca237
commit b46d12f86d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
convert.py
View File

@ -1036,7 +1036,8 @@ def load_some_model(path: Path) -> ModelPlus:
# Be extra-friendly and accept either a file or a directory: # Be extra-friendly and accept either a file or a directory:
if path.is_dir(): if path.is_dir():
# Check if it's a set of safetensors files first # Check if it's a set of safetensors files first
files = list(path.glob("model-00001-of-*.safetensors")) globs = ["model-00001-of-*.safetensors", "model.safetensors"]
files = [file for glob in globs for file in path.glob(glob)]
if not files: if not files:
# Try the PyTorch patterns too, with lower priority # Try the PyTorch patterns too, with lower priority
globs = ["consolidated.00.pth", "pytorch_model-00001-of-*.bin", "*.pt", "pytorch_model.bin"] globs = ["consolidated.00.pth", "pytorch_model-00001-of-*.bin", "*.pt", "pytorch_model.bin"]
@ -1123,7 +1124,7 @@ def main(args_in: list[str] | None = None) -> None:
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("--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, *.safetensors)")
parser.add_argument("--vocabtype", choices=["spm", "bpe"], help="vocab format (default: spm)", default="spm") parser.add_argument("--vocabtype", choices=["spm", "bpe"], help="vocab format (default: spm)", default="spm")
parser.add_argument("--ctx", type=int, help="model training context (default: based on input)") parser.add_argument("--ctx", type=int, help="model training context (default: based on input)")
parser.add_argument("--concurrency", type=int, help=f"concurrency used for conversion (default: {DEFAULT_CONCURRENCY})", default = DEFAULT_CONCURRENCY) parser.add_argument("--concurrency", type=int, help=f"concurrency used for conversion (default: {DEFAULT_CONCURRENCY})", default = DEFAULT_CONCURRENCY)