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

When loading a safetensors file, ignore the metadata header; If no pt or pth files are available, attempt to load safetensors files

Browse source
This commit is contained in:
ubik2 2023-05-02 02:47:35 -07:00
parent f4cef87edf
commit b8279c82d0
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

@ -750,7 +750,7 @@ 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)
@ -1037,6 +1037,10 @@ def load_some_model(path: Path) -> ModelPlus:
if path.is_dir(): if path.is_dir():
globs = ["consolidated.00.pth", "pytorch_model-00001-of-*.bin", "*.pt"] globs = ["consolidated.00.pth", "pytorch_model-00001-of-*.bin", "*.pt"]
files = [file for glob in globs for file in path.glob(glob)] files = [file for glob in globs for file in path.glob(glob)]
if not files:
# Check if it's a set of safetensors files
globs = ["model-00001-of-*.safetensors"]
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