Update README.md (#3)
Browse files- Update README.md (8e07ef9bb64b51687cde799feee406d64123ae32)
Co-authored-by: laixinn <[email protected]>
README.md
CHANGED
@@ -28,7 +28,7 @@ The weight scales are determined by dividing the block-wise maximum of element v
|
|
28 |
To generate this weight, run the provided script in the ``./inference`` directory:
|
29 |
|
30 |
``
|
31 |
-
python3
|
32 |
``
|
33 |
|
34 |
---
|
|
|
28 |
To generate this weight, run the provided script in the ``./inference`` directory:
|
29 |
|
30 |
``
|
31 |
+
python3 bf16_cast_block_int8.py --input-bf16-hf-path /path/to/bf16-weights/ --output-int8-hf-path /path/to/save-int8-weight/
|
32 |
``
|
33 |
|
34 |
---
|