das
Browse files
README.md
CHANGED
|
@@ -1,3 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# NEPALI BERT
|
| 2 |
## Masked Language Model for nepali language trained on nepali news scrapped from different nepali news website. The data set contained about 10 million of nepali sentences mainly related to nepali news.
|
| 3 |
|
|
@@ -36,4 +47,4 @@ from pprint import pprint pprint(fill_mask(f"तिमीलाई कस्त
|
|
| 36 |
|
| 37 |
## Data Description
|
| 38 |
Trained on about 4.6 GB of Nepali text corpus collected from various sources
|
| 39 |
-
These data were collected from nepali news site, OSCAR nepali corpus
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- Shushant/nepali
|
| 5 |
+
language:
|
| 6 |
+
- ne
|
| 7 |
+
metrics:
|
| 8 |
+
- perplexity
|
| 9 |
+
library_name: transformers
|
| 10 |
+
pipeline_tag: fill-mask
|
| 11 |
+
---
|
| 12 |
# NEPALI BERT
|
| 13 |
## Masked Language Model for nepali language trained on nepali news scrapped from different nepali news website. The data set contained about 10 million of nepali sentences mainly related to nepali news.
|
| 14 |
|
|
|
|
| 47 |
|
| 48 |
## Data Description
|
| 49 |
Trained on about 4.6 GB of Nepali text corpus collected from various sources
|
| 50 |
+
These data were collected from nepali news site, OSCAR nepali corpus
|