Commit
•
5b824f1
1
Parent(s):
877143a
Update README.md
Browse files
README.md
CHANGED
|
@@ -26,6 +26,8 @@ The model was trained with the parameters:
|
|
| 26 |
{'batch_size': 128}
|
| 27 |
```
|
| 28 |
|
|
|
|
|
|
|
| 29 |
**Loss**:
|
| 30 |
|
| 31 |
`sentence_transformers.losses.MultipleNegativesRankingLoss.MNRLGradCache`
|
|
|
|
| 26 |
{'batch_size': 128}
|
| 27 |
```
|
| 28 |
|
| 29 |
+
The model uses BitFit, weighted mean pooling & GradCache, for details see: https://arxiv.org/abs/2202.08904
|
| 30 |
+
|
| 31 |
**Loss**:
|
| 32 |
|
| 33 |
`sentence_transformers.losses.MultipleNegativesRankingLoss.MNRLGradCache`
|