Update README.md
Browse files
README.md
CHANGED
|
@@ -19,4 +19,8 @@ license: apache-2.0
|
|
| 19 |
---
|
| 20 |
# Transformer language model for Croatian and Serbian
|
| 21 |
Trained on 10GB datasets that contain Croatian and Serbian language for two epochs (500k steps).
|
| 22 |
-
Leipzig, OSCAR and srWac datasets
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
---
|
| 20 |
# Transformer language model for Croatian and Serbian
|
| 21 |
Trained on 10GB datasets that contain Croatian and Serbian language for two epochs (500k steps).
|
| 22 |
+
Leipzig, OSCAR and srWac datasets
|
| 23 |
+
|
| 24 |
+
| Model | #params | Arch. | Training data |
|
| 25 |
+
|--------------------------------|--------------------------------|-------|-----------------------------------|
|
| 26 |
+
| `Andrija/SRoBERTa-base` | 80M | Third | Leipzig Corpus, OSCAR and srWac (10 GB of text) |
|