Update model card
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ tags:
|
|
| 5 |
- text-classfication
|
| 6 |
- int8
|
| 7 |
- Intel® Neural Compressor
|
|
|
|
| 8 |
- PostTrainingStatic
|
| 9 |
datasets:
|
| 10 |
- mrpc
|
|
@@ -34,7 +35,7 @@ The linear module **bert.encoder.layer.9.output.dense** falls back to fp32 to me
|
|
| 34 |
### Load with Intel® Neural Compressor:
|
| 35 |
|
| 36 |
```python
|
| 37 |
-
from optimum.intel.neural_compressor
|
| 38 |
int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
|
| 39 |
'Intel/bert-base-uncased-mrpc-int8-static',
|
| 40 |
)
|
|
|
|
| 5 |
- text-classfication
|
| 6 |
- int8
|
| 7 |
- Intel® Neural Compressor
|
| 8 |
+
- neural-compressor
|
| 9 |
- PostTrainingStatic
|
| 10 |
datasets:
|
| 11 |
- mrpc
|
|
|
|
| 35 |
### Load with Intel® Neural Compressor:
|
| 36 |
|
| 37 |
```python
|
| 38 |
+
from optimum.intel.neural_compressor import IncQuantizedModelForSequenceClassification
|
| 39 |
int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
|
| 40 |
'Intel/bert-base-uncased-mrpc-int8-static',
|
| 41 |
)
|