Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ language:
|
|
| 5 |
- en
|
| 6 |
---
|
| 7 |
|
| 8 |
-
This is a pruned version of the
|
| 9 |
The chosen vocabulary has 30K norwegian, english and special tokens, ~12% of the old size. This reduces the model size by roughly 37%.
|
| 10 |
The model is still OK on similar languages, like German and Danish, but very different languages like arabic is no longer understood.
|
| 11 |
This model is intended as starting point for finetuning mt5 for norwegian applications.
|
|
|
|
| 5 |
- en
|
| 6 |
---
|
| 7 |
|
| 8 |
+
This is a pruned version of the ```google/mt5-large``` model. Here, the input and output embeddings are pruned to support a greatly reduced vocabulary.
|
| 9 |
The chosen vocabulary has 30K norwegian, english and special tokens, ~12% of the old size. This reduces the model size by roughly 37%.
|
| 10 |
The model is still OK on similar languages, like German and Danish, but very different languages like arabic is no longer understood.
|
| 11 |
This model is intended as starting point for finetuning mt5 for norwegian applications.
|