Update README.md
Browse files
README.md
CHANGED
|
@@ -18,4 +18,12 @@ license: apache-2.0
|
|
| 18 |
---
|
| 19 |
# Transformer language model for Croatian and Serbian
|
| 20 |
Trained on 3GB datasets that contain Croatian and Serbian language for two epochs.
|
| 21 |
-
Leipzig and OSCAR datasets
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
---
|
| 19 |
# Transformer language model for Croatian and Serbian
|
| 20 |
Trained on 3GB datasets that contain Croatian and Serbian language for two epochs.
|
| 21 |
+
Leipzig and OSCAR datasets
|
| 22 |
+
|
| 23 |
+
# Information of dataset
|
| 24 |
+
|
| 25 |
+
| Model | #params | Arch. | Training data |
|
| 26 |
+
|
| 27 |
+
|--------------------------------|--------------------------------|-------|-----------------------------------|
|
| 28 |
+
|
| 29 |
+
| `Andrija/SRoBERTa` | 80M | First | Leipzig Corpus and OSCAR (3 GB of text) |
|