Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,7 @@ license: mit
|
|
5 |
tags:
|
6 |
- text-classfication
|
7 |
- int8
|
8 |
-
- Neural Compressor
|
9 |
- PostTrainingStatic
|
10 |
datasets:
|
11 |
- glue
|
@@ -45,7 +45,7 @@ The calibration dataloader is the train dataloader. The default calibration samp
|
|
45 |
| **Accuracy (eval-f1)** |0.9007|0.8983|
|
46 |
| **Model size (MB)** |14|51.8|
|
47 |
|
48 |
-
### Load with Intel® Neural Compressor
|
49 |
|
50 |
```python
|
51 |
from neural_compressor.utils.load_huggingface import OptimizedModel
|
|
|
5 |
tags:
|
6 |
- text-classfication
|
7 |
- int8
|
8 |
+
- Intel® Neural Compressor
|
9 |
- PostTrainingStatic
|
10 |
datasets:
|
11 |
- glue
|
|
|
45 |
| **Accuracy (eval-f1)** |0.9007|0.8983|
|
46 |
| **Model size (MB)** |14|51.8|
|
47 |
|
48 |
+
### Load with Intel® Neural Compressor:
|
49 |
|
50 |
```python
|
51 |
from neural_compressor.utils.load_huggingface import OptimizedModel
|