Commit
•
11dae5a
1
Parent(s):
69c7571
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,9 +38,6 @@ Key Features:
|
|
| 38 |
- Fine-tuning performed for 3 epochs with a batch size of 16.
|
| 39 |
- Learning rate: 2e-5.
|
| 40 |
- MLM Probability: 15%.
|
| 41 |
-
- **Tools**:
|
| 42 |
-
- **Hugging Face Transformers Library**
|
| 43 |
-
- **PyTorch**
|
| 44 |
|
| 45 |
## Evaluation Results
|
| 46 |
|
|
@@ -78,6 +75,7 @@ top_5_tokens = torch.topk(mask_token_logits, 5, dim=1).indices[0].tolist()
|
|
| 78 |
predicted_words = [tokenizer.decode([token]) for token in top_5_tokens]
|
| 79 |
|
| 80 |
print(f"Predicted words: {predicted_words}")
|
|
|
|
| 81 |
|
| 82 |
|
| 83 |
@misc{EgBERT,
|
|
|
|
| 38 |
- Fine-tuning performed for 3 epochs with a batch size of 16.
|
| 39 |
- Learning rate: 2e-5.
|
| 40 |
- MLM Probability: 15%.
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
## Evaluation Results
|
| 43 |
|
|
|
|
| 75 |
predicted_words = [tokenizer.decode([token]) for token in top_5_tokens]
|
| 76 |
|
| 77 |
print(f"Predicted words: {predicted_words}")
|
| 78 |
+
,,,
|
| 79 |
|
| 80 |
|
| 81 |
@misc{EgBERT,
|