Update README.md
Browse files
README.md
CHANGED
@@ -30,7 +30,7 @@ The original fp32 model comes from the fine-tuned model [Intel/bert-base-uncased
|
|
30 |
| **Accuracy (eval-f1)** |0.9153|0.9042|
|
31 |
| **Model size (MB)** |174|418|
|
32 |
|
33 |
-
### Load with
|
34 |
|
35 |
```python
|
36 |
from neural_compressor.utils.load_huggingface import OptimizedModel
|
|
|
30 |
| **Accuracy (eval-f1)** |0.9153|0.9042|
|
31 |
| **Model size (MB)** |174|418|
|
32 |
|
33 |
+
### Load with Intel® Neural Compressor (build from source):
|
34 |
|
35 |
```python
|
36 |
from neural_compressor.utils.load_huggingface import OptimizedModel
|