Update README.md
Browse files
README.md
CHANGED
|
@@ -48,7 +48,3 @@ int8_model = OptimizedModel.from_pretrained(
|
|
| 48 |
'Intel/bart-large-mrpc-int8-dynamic',
|
| 49 |
)
|
| 50 |
```
|
| 51 |
-
|
| 52 |
-
Notes:
|
| 53 |
-
- The INT8 model has better performance than the FP32 model when the CPU is fully occupied. Otherwise, there will be the illusion that INT8 is inferior to FP32.
|
| 54 |
-
|
|
|
|
| 48 |
'Intel/bart-large-mrpc-int8-dynamic',
|
| 49 |
)
|
| 50 |
```
|
|
|
|
|
|
|
|
|
|
|
|