Commit
•
a5dea88
1
Parent(s):
4393c88
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,10 @@ license: apache-2.0
|
|
| 3 |
language:
|
| 4 |
- hu
|
| 5 |
- en
|
| 6 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
language:
|
| 4 |
- hu
|
| 5 |
- en
|
| 6 |
+
---
|
| 7 |
+
This is a smaller version of the [google/mt5-large](https://huggingface.co/google/mt5-large) model with only Hungarian and some English embeddings left.
|
| 8 |
+
|
| 9 |
+
After shrinking the sentencepiece vocabulary from 250K to 50K (top 10K English and top 40K Hungarian tokens) the model size reduced from 4.92GB to 3.28GB.
|
| 10 |
+
|
| 11 |
+
This model is based on the description of [cointegrated/rut5-base](https://huggingface.co/cointegrated/rut5-base).
|
| 12 |
+
The creation of this model is described in the post [How to adapt a multilingual T5 model for a single language](https://towardsdatascience.com/how-to-adapt-a-multilingual-t5-model-for-a-single-language-b9f94f3d9c90) along with the source code.
|