Commit
•
2d22c94
1
Parent(s):
78eb317
Add link to demo space
Browse files
README.md
CHANGED
|
@@ -23,6 +23,8 @@ Our final optimized model weighs **579 MB**, has an inference speed of **18.184
|
|
| 23 |
| [madlag/bert-large-uncased-wwm-squadv2-x2.63-f82.6-d16-hybrid-v1](https://huggingface.co/madlag/bert-large-uncased-wwm-squadv2-x2.63-f82.6-d16-hybrid-v1) | 1085 MB | 90.801 ms | 82.67% |
|
| 24 |
| Our optimized model | 579 MB | 18.184 ms | 82.68% |
|
| 25 |
|
|
|
|
|
|
|
| 26 |
## Example Usage
|
| 27 |
|
| 28 |
```python
|
|
|
|
| 23 |
| [madlag/bert-large-uncased-wwm-squadv2-x2.63-f82.6-d16-hybrid-v1](https://huggingface.co/madlag/bert-large-uncased-wwm-squadv2-x2.63-f82.6-d16-hybrid-v1) | 1085 MB | 90.801 ms | 82.67% |
|
| 24 |
| Our optimized model | 579 MB | 18.184 ms | 82.68% |
|
| 25 |
|
| 26 |
+
You can test the inference of those models on [tryolabs/transformers-optimization space](https://huggingface.co/spaces/tryolabs/transformers-optimization)
|
| 27 |
+
|
| 28 |
## Example Usage
|
| 29 |
|
| 30 |
```python
|