Commit
•
81c16d6
1
Parent(s):
3047552
Update README
Browse files
README.md
CHANGED
|
@@ -1,12 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
language: uz
|
| 3 |
tags:
|
| 4 |
- uzbert
|
| 5 |
- uzbek
|
| 6 |
- bert
|
|
|
|
| 7 |
license: MIT
|
| 8 |
datasets:
|
| 9 |
-
- webcrawl
|
| 10 |
---
|
| 11 |
|
| 12 |
# UzBERT base model (uncased)
|
|
@@ -59,4 +60,4 @@ You can use this model directly with a pipeline for masked language modeling:
|
|
| 59 |
|
| 60 |
## Training data
|
| 61 |
|
| 62 |
-
UzBERT model was pretrained on
|
|
|
|
| 1 |
---
|
| 2 |
+
language: uz
|
| 3 |
tags:
|
| 4 |
- uzbert
|
| 5 |
- uzbek
|
| 6 |
- bert
|
| 7 |
+
- cyrillic
|
| 8 |
license: MIT
|
| 9 |
datasets:
|
| 10 |
+
- webcrawl
|
| 11 |
---
|
| 12 |
|
| 13 |
# UzBERT base model (uncased)
|
|
|
|
| 60 |
|
| 61 |
## Training data
|
| 62 |
|
| 63 |
+
UzBERT model was pretrained on \~625K news articles (\~142M words).
|