Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,7 @@ library_name: transformers
|
|
| 3 |
license: mit
|
| 4 |
datasets:
|
| 5 |
- domce20/c4-lithuanian-enhanced
|
|
|
|
| 6 |
language:
|
| 7 |
- lt
|
| 8 |
---
|
|
@@ -14,4 +15,6 @@ GPT-2 based model trained for Lithuanian.
|
|
| 14 |
|
| 15 |
### Model Description
|
| 16 |
|
| 17 |
-
The model architecture is copied from the ai-forever/mGPT model, however it is trained from scratch on a modified partition of the Lithuanian partition of the mC4 dataset.
|
|
|
|
|
|
|
|
|
| 3 |
license: mit
|
| 4 |
datasets:
|
| 5 |
- domce20/c4-lithuanian-enhanced
|
| 6 |
+
- allenai/c4
|
| 7 |
language:
|
| 8 |
- lt
|
| 9 |
---
|
|
|
|
| 15 |
|
| 16 |
### Model Description
|
| 17 |
|
| 18 |
+
The model architecture is copied from the ai-forever/mGPT model, however it is trained from scratch on a modified partition of the Lithuanian partition of the mC4 dataset.
|
| 19 |
+
|
| 20 |
+
The training was done on Vilnius University supercomputer.
|