root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-30 21:34:36 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

convert-llama-h5-to-gguf.py : simplify nbytes

Browse Source
This commit is contained in:
klosax 2023-08-12 22:30:35 +02:00 committed by GitHub
parent f8218477b3
commit e606ffeaee
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
convert-llama-h5-to-gguf.py
View File

@ -196,17 +196,7 @@ for name in list_vars.keys():
# if f16 desired, convert any float32 2-dim weight tensors to float16 # if f16 desired, convert any float32 2-dim weight tensors to float16
data_dtype = np.float16 data_dtype = np.float16
nelements = 1 data_nbytes = data.size * 2 if data_dtype == np.float16 else data.size * 4
for i in range(n_dims):
nelements *= data.shape[n_dims - 1 - i]
data_nbytes = 0
if data_dtype == np.float16:
data_nbytes = nelements * 2
elif data_dtype == np.float32:
data_nbytes = nelements * 4
gguf_writer.add_tensor_info(name, data.shape, data_dtype, data_nbytes) gguf_writer.add_tensor_info(name, data.shape, data_dtype, data_nbytes)