Commit
·
d1b3907
1
Parent(s):
92a58af
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ After shrinking the sentencepiece vocabulary from 250K to 30K (top 10K English a
|
|
| 21 |
the number of model parameters reduced to 244M parameters, and model size reduced from 2.2GB to 0.9GB - 42% of the original one.
|
| 22 |
|
| 23 |
|
| 24 |
-
This model is based on the description of
|
| 25 |
The creation of this model is described in the post "How to adapt a multilingual T5 model for a single language" along with the source code.
|
| 26 |
|
| 27 |
- **Developed by:** [Gábor Madarász]
|
|
|
|
| 21 |
the number of model parameters reduced to 244M parameters, and model size reduced from 2.2GB to 0.9GB - 42% of the original one.
|
| 22 |
|
| 23 |
|
| 24 |
+
This model is based on the description of [cointegrated/rut5-base](https://huggingface.co/cointegrated/rut5-base).
|
| 25 |
The creation of this model is described in the post "How to adapt a multilingual T5 model for a single language" along with the source code.
|
| 26 |
|
| 27 |
- **Developed by:** [Gábor Madarász]
|