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

export norms as f32

Browse source
This commit is contained in:
slaren 2024-04-06 22:33:36 +02:00
parent 26e8f23bf3
commit ce9413d849
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert-hf-to-gguf.py
View file

@ -160,7 +160,7 @@ class Model(ABC):
data = data.astype(np.float32)
# TODO: Why cant we use these float16 as-is? There should be not reason to store float16 as float32
if self.ftype == 1 and data_dtype == np.float16 and n_dims == 1:
if self.ftype == 1 and data_dtype == np.float16 and (n_dims == 1 or new_name.endswith("_norm.weight")):
data = data.astype(np.float32)
# if f16 desired, convert any float32 2-dim weight tensors to float16