Commit
•
f7483ec
1
Parent(s):
5795029
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ru
|
| 4 |
+
- myv
|
| 5 |
+
tags:
|
| 6 |
+
- erzya
|
| 7 |
+
- mordovian
|
| 8 |
+
- fill-mask
|
| 9 |
+
- pretraining
|
| 10 |
+
- embeddings
|
| 11 |
+
- masked-lm
|
| 12 |
+
- feature-extraction
|
| 13 |
+
- sentence-similarity
|
| 14 |
+
license: cc-by-sa-4.0
|
| 15 |
+
datasets:
|
| 16 |
+
- slone/myv_ru_2022
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
This is a version of [LaBSE-en-ru-myv-v1](https://huggingface.co/slone/LaBSE-en-ru-myv-v1), fine-tuned for about 150K steps
|
| 20 |
+
on the [myv_ru_2022](https://huggingface.co/datasets/slone/myv_ru_2022) dataset, in
|
| 21 |
+
[this notebook](https://colab.research.google.com/drive/1SxeraKZS6KYKobzVNNyIQZa4WnhpJ_nb?usp=sharing).
|
| 22 |
+
|
| 23 |
+
It demonstrates slighly better results than the v1 model, both on bitext mining and on the MLM task.
|