carsonhxsu
commited on
Commit
•
8388800
1
Parent(s):
7fa8e23
update README
Browse files
README.md
CHANGED
@@ -26,7 +26,7 @@ We use the Baichuan2-7B-Base and Baichuan2-13B-Base model for measurement, but t
|
|
26 |
|
27 |
## Speed
|
28 |
|
29 |
-
* Evaluated at tokens/s
|
30 |
* test on A100 40G
|
31 |
* MEMOPT mode
|
32 |
|
|
|
26 |
|
27 |
## Speed
|
28 |
|
29 |
+
* Evaluated at tokens/s (#tokens of input and output divided by inference time cost)
|
30 |
* test on A100 40G
|
31 |
* MEMOPT mode
|
32 |
|