Update model card
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ license: mit
|
|
| 5 |
tags:
|
| 6 |
- text-classfication
|
| 7 |
- int8
|
|
|
|
| 8 |
- Intel® Neural Compressor
|
| 9 |
- PostTrainingStatic
|
| 10 |
datasets:
|
|
@@ -46,8 +47,9 @@ The calibration dataloader is the train dataloader. The default calibration samp
|
|
| 46 |
### Load with Intel® Neural Compressor:
|
| 47 |
|
| 48 |
```python
|
| 49 |
-
from neural_compressor.
|
| 50 |
-
|
| 51 |
-
|
|
|
|
| 52 |
)
|
| 53 |
```
|
|
|
|
| 5 |
tags:
|
| 6 |
- text-classfication
|
| 7 |
- int8
|
| 8 |
+
- neural-compressor
|
| 9 |
- Intel® Neural Compressor
|
| 10 |
- PostTrainingStatic
|
| 11 |
datasets:
|
|
|
|
| 47 |
### Load with Intel® Neural Compressor:
|
| 48 |
|
| 49 |
```python
|
| 50 |
+
from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
|
| 51 |
+
|
| 52 |
+
int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
|
| 53 |
+
"Intel/xlnet-base-cased-mrpc-int8-static",
|
| 54 |
)
|
| 55 |
```
|