Update README.md
Browse files
README.md
CHANGED
|
@@ -13,8 +13,9 @@ license: mit
|
|
| 13 |
|
| 14 |
Please check the [official repository](https://github.com/microsoft/DeBERTa) for more details and updates.
|
| 15 |
|
|
|
|
|
|
|
| 16 |
This is the DeBERTa V3 large model with 24 layers, 1024 hidden size. Total parameters is 418M while Embedding layer takes about 131M due to the usage of 128k vocabulary. It's trained with 160GB data.
|
| 17 |
-
For more details of our V3 model, please check appendix A11 in our paper.
|
| 18 |
|
| 19 |
#### Fine-tuning on NLU tasks
|
| 20 |
|
|
|
|
| 13 |
|
| 14 |
Please check the [official repository](https://github.com/microsoft/DeBERTa) for more details and updates.
|
| 15 |
|
| 16 |
+
In DeBERTa V3 we replaced MLM objective with RTD(Replaced Token Detection) objective during pre-training, which significantly improves the model performance. Please check appendix A11 in our paper for more details.
|
| 17 |
+
|
| 18 |
This is the DeBERTa V3 large model with 24 layers, 1024 hidden size. Total parameters is 418M while Embedding layer takes about 131M due to the usage of 128k vocabulary. It's trained with 160GB data.
|
|
|
|
| 19 |
|
| 20 |
#### Fine-tuning on NLU tasks
|
| 21 |
|