Andrei Panferov commited on
Commit ·
a0e367f
1
Parent(s): dccb954
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ru
|
| 4 |
+
tags:
|
| 5 |
+
- PyTorch
|
| 6 |
+
- Transformers
|
| 7 |
+
|
| 8 |
+
---
|
| 9 |
+
# ebanko-base
|
| 10 |
+
Model was finetuned by [black_samorez](https://github.com/BlackSamorez).
|
| 11 |
+
|
| 12 |
+
Based off [sberbank-ai/ruT5-base](https://huggingface.co/sberbank-ai/ruT5-base).
|
| 13 |
+
|
| 14 |
+
Finetuned on [Russian Language Toxic Comments](https://www.kaggle.com/datasets/blackmoon/russian-language-toxic-comments) and [
|
| 15 |
+
russe_detox_2022](https://github.com/skoltech-nlp/russe_detox_2022) train to toxify text.
|
| 16 |
+
* Task: `text2text generation`
|
| 17 |
+
* Type: `encoder-decoder`
|
| 18 |
+
* Tokenizer: `bpe`
|
| 19 |
+
* Dict size: `32 101`
|
| 20 |
+
* Num Parameters: `222 M`
|
| 21 |
+
|
| 22 |
---
|
| 23 |
license: apache-2.0
|
| 24 |
---
|