saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-27 22:45:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix a bug in 4bits quantizer script (#18878)

Browse source 
### Description
<!-- Describe your changes. -->



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
This commit is contained in:
Ye Wang 2023-12-20 06:53:33 +00:00 committed by GitHub
parent 666fcbde4d
commit 02eb17655d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py
View file

@ -193,9 +193,13 @@ set of 4b integers with a scaling factor and an optional offset.
parser.add_argument("--input_model", required=True, help="Path to the input model file")
parser.add_argument("--output_model", required=True, help="Path to the output model file")
parser.add_argument("--block_size", required=False, default=32)
parser.add_argument("--block_size", required=False, default=32, type=int, help="Block size for quantization")
parser.add_argument(
"--symmetric", required=False, default=True, help="Indicate whether to quantize the model symmetrically"
"--symmetric",
required=False,
default=True,
type=bool,
help="Indicate whether to quantize the model symmetrically",
)
parser.add_argument("-v", "--verbose", required=False, action="store_true")
parser.set_defaults(verbose=False)