Update README.md
Browse files
README.md
CHANGED
|
@@ -60,6 +60,7 @@ metrics:
|
|
| 60 |
- pearsonr
|
| 61 |
- mae
|
| 62 |
- r_squared
|
|
|
|
| 63 |
---
|
| 64 |
|
| 65 |
|
|
@@ -79,7 +80,8 @@ This model is for reference-free quality estimation (QE) of machine translation
|
|
| 79 |
|
| 80 |
### Training hyperparameters
|
| 81 |
|
| 82 |
-
This version of the model uses `tokenizer.model_max_length=512`.
|
|
|
|
| 83 |
|
| 84 |
The following hyperparameters were used during training:
|
| 85 |
- learning_rate: 8e-05
|
|
|
|
| 60 |
- pearsonr
|
| 61 |
- mae
|
| 62 |
- r_squared
|
| 63 |
+
new_version: ymoslem/ModernBERT-large-qe-v1
|
| 64 |
---
|
| 65 |
|
| 66 |
|
|
|
|
| 80 |
|
| 81 |
### Training hyperparameters
|
| 82 |
|
| 83 |
+
This version of the model uses `tokenizer.model_max_length=512`.
|
| 84 |
+
The model with full length of 8192 can be found here [ymoslem/ModernBERT-large-qe-v1](https://huggingface.co/ymoslem/ModernBERT-large-qe-v1/)
|
| 85 |
|
| 86 |
The following hyperparameters were used during training:
|
| 87 |
- learning_rate: 8e-05
|