Update README.md
Browse files
README.md
CHANGED
|
@@ -28,15 +28,14 @@ Finetuned mT5-Model for German sentence-level text-simplification.
|
|
| 28 |
|
| 29 |
### Training Data
|
| 30 |
|
| 31 |
-
[DEplain/DEplain-APA-sent](https://huggingface.co/datasets/DEplain/DEplain-APA-sent)
|
| 32 |
|
| 33 |
### Training Procedure
|
| 34 |
|
| 35 |
Parameter-efficient Fine-Tuning with LoRA.
|
| 36 |
|
| 37 |
-
Vocabulary adjusted through Vocabulary Transfer (Mosin et al. ([](arXiv:2112.14569))
|
| 38 |
|
| 39 |
-
|
| 40 |
#### Training Hyperparameters
|
| 41 |
* Batch Size: 16
|
| 42 |
* Epochs: 1
|
|
|
|
| 28 |
|
| 29 |
### Training Data
|
| 30 |
|
| 31 |
+
[DEplain/DEplain-APA-sent](https://huggingface.co/datasets/DEplain/DEplain-APA-sent) Stodden et al. (2023):[arXiv:2305.18939](arXiv:2305.18939)
|
| 32 |
|
| 33 |
### Training Procedure
|
| 34 |
|
| 35 |
Parameter-efficient Fine-Tuning with LoRA.
|
| 36 |
|
| 37 |
+
Vocabulary adjusted through Vocabulary Transfer (Mosin et al. (2021): [arXiv:2112.14569](arXiv:2112.14569)).
|
| 38 |
|
|
|
|
| 39 |
#### Training Hyperparameters
|
| 40 |
* Batch Size: 16
|
| 41 |
* Epochs: 1
|