mirror of
https://git.adityakumar.xyz/llama.cpp.git
synced 2024-11-09 15:29:43 +00:00
convert: add ability to convert safetensors files (#1276)
* when loading a safetensors file, ignore the metadata header * check for safetensors files first, and only use PyTorch versions when safetensors aren't available
This commit is contained in:
parent
1f48b0abcf
commit
95078cc554
1 changed files with 7 additions and 3 deletions
10
convert.py
10
convert.py
|
@ -766,7 +766,7 @@ def lazy_load_safetensors_file(fp: IO[bytes], path: Path) -> ModelPlus:
|
||||||
return UnquantizedTensor(np.frombuffer(buf, dtype=numpy_dtype).reshape(shape))
|
return UnquantizedTensor(np.frombuffer(buf, dtype=numpy_dtype).reshape(shape))
|
||||||
description = f'safetensors begin={begin} end={end} type={data_type} path={path}'
|
description = f'safetensors begin={begin} end={end} type={data_type} path={path}'
|
||||||
return LazyTensor(load, shape, data_type, description)
|
return LazyTensor(load, shape, data_type, description)
|
||||||
model = {name: convert(info) for (name, info) in header.items()}
|
model = {name: convert(info) for (name, info) in header.items() if name != '__metadata__'}
|
||||||
return ModelPlus(model=model, paths=[path], format='safetensors', vocab=None)
|
return ModelPlus(model=model, paths=[path], format='safetensors', vocab=None)
|
||||||
|
|
||||||
|
|
||||||
|
@ -1051,8 +1051,12 @@ def load_some_model(path: Path) -> ModelPlus:
|
||||||
'''Load a model of any supported format.'''
|
'''Load a model of any supported format.'''
|
||||||
# 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():
|
||||||
globs = ["consolidated.00.pth", "pytorch_model-00001-of-*.bin", "*.pt"]
|
# Check if it's a set of safetensors files first
|
||||||
files = [file for glob in globs for file in path.glob(glob)]
|
files = list(path.glob("model-00001-of-*.safetensors"))
|
||||||
|
if not files:
|
||||||
|
# Try the PyTorch patterns too, with lower priority
|
||||||
|
globs = ["consolidated.00.pth", "pytorch_model-00001-of-*.bin", "*.pt"]
|
||||||
|
files = [file for glob in globs for file in path.glob(glob)]
|
||||||
if not files:
|
if not files:
|
||||||
# Try GGML too, but with lower priority, since if both a non-GGML
|
# Try GGML too, but with lower priority, since if both a non-GGML
|
||||||
# model and a GGML model exist in the same directory, we assume the
|
# model and a GGML model exist in the same directory, we assume the
|
||||||
|
|
Loading…
Reference in a new issue