Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,9 @@ It comes in two sizes:
|
|
| 18 |
- **VBART-Large**: 387M parameters
|
| 19 |
- **VBART-XLarge**: 740M parameters
|
| 20 |
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
- **Developed by:** [VNGRS-AI](https://vngrs.com/ai/)
|
| 23 |
- **Model type:** Transformer encoder-decoder based on mBART architecture
|
|
|
|
| 18 |
- **VBART-Large**: 387M parameters
|
| 19 |
- **VBART-XLarge**: 740M parameters
|
| 20 |
|
| 21 |
+
VBART-XLarge is created by adding extra Transformer layers between the layers of VBART-Large. Hence it was able to transfer learned weights from the smaller model while doublings its number of layers.
|
| 22 |
+
VBART-XLarge improves the results compared to VBART-Large albeit in small margins.
|
| 23 |
+
|
| 24 |
|
| 25 |
- **Developed by:** [VNGRS-AI](https://vngrs.com/ai/)
|
| 26 |
- **Model type:** Transformer encoder-decoder based on mBART architecture
|