root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

gguf-py : fix dtype check (#6045)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-03-14 13:32:14 +02:00
parent 15a333260a
commit 77178eedc8
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/gguf/gguf_writer.py
View File

@ -204,7 +204,7 @@ class GGUFWriter:
for i in range(n_dims): for i in range(n_dims):
self.ti_data += self._pack("Q", tensor_shape[n_dims - 1 - i]) self.ti_data += self._pack("Q", tensor_shape[n_dims - 1 - i])
if raw_dtype is None: if raw_dtype is None:
if tensor_shape == np.float32: if tensor_dtype == np.float32:
dtype = GGMLQuantizationType.F32 dtype = GGMLQuantizationType.F32
elif tensor_dtype == np.float16: elif tensor_dtype == np.float16:
dtype = GGMLQuantizationType.F16 dtype = GGMLQuantizationType.F16