add neural-compressor tag
Browse files
README.md
CHANGED
|
@@ -1,14 +1,16 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
-
-
|
| 5 |
-
-
|
| 6 |
-
-
|
| 7 |
-
-
|
|
|
|
|
|
|
| 8 |
datasets:
|
| 9 |
-
- squad
|
| 10 |
metrics:
|
| 11 |
-
- f1
|
| 12 |
---
|
| 13 |
|
| 14 |
# INT8 DistilBERT base uncased finetuned on Squad
|
|
@@ -62,4 +64,4 @@ The calibration dataloader is the eval dataloader. The default calibration sampl
|
|
| 62 |
```python
|
| 63 |
from optimum.onnxruntime import ORTModelForQuestionAnswering
|
| 64 |
model = ORTModelForQuestionAnswering.from_pretrained('Intel/distilbert-base-uncased-distilled-squad-int8-static')
|
| 65 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
+
- neural-compressor
|
| 5 |
+
- 8-bit
|
| 6 |
+
- int8
|
| 7 |
+
- Intel® Neural Compressor
|
| 8 |
+
- PostTrainingStatic
|
| 9 |
+
- onnx
|
| 10 |
datasets:
|
| 11 |
+
- squad
|
| 12 |
metrics:
|
| 13 |
+
- f1
|
| 14 |
---
|
| 15 |
|
| 16 |
# INT8 DistilBERT base uncased finetuned on Squad
|
|
|
|
| 64 |
```python
|
| 65 |
from optimum.onnxruntime import ORTModelForQuestionAnswering
|
| 66 |
model = ORTModelForQuestionAnswering.from_pretrained('Intel/distilbert-base-uncased-distilled-squad-int8-static')
|
| 67 |
+
```
|