Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,43 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- hu
|
6 |
+
tags:
|
7 |
+
- translation
|
8 |
+
license: apache-2.0
|
9 |
+
metrics:
|
10 |
+
- sacrebleu
|
11 |
+
- chrf
|
12 |
+
widget:
|
13 |
+
- text: "This may not make much sense to you, sir, but I'd like to ask your permission to date your daughter."
|
14 |
---
|
15 |
+
|
16 |
+
# 12-lingual Hungarian-centered finetuned M2M100_1.2B model
|
17 |
+
|
18 |
+
For further details, see or [our demo site](https://juniper.nytud.hu/demo/nlp).
|
19 |
+
|
20 |
+
- Source language: Bulgarian (bg), Czech (cs), German (de), English (en), Croatian (hr), Polish, (pl), Romanian (ro), Russian (ru), Slovak (sk), Slovene (sl), Serbian (sr), Ukrainian (uk)
|
21 |
+
- Target language: Hungarian (hu)
|
22 |
+
|
23 |
+
- Finetuned on subcorpora from OPUS
|
24 |
+
- Segments: 3 million per language
|
25 |
+
|
26 |
+
## Limitations
|
27 |
+
|
28 |
+
- max_source_length: 256
|
29 |
+
- max_target_length: 256
|
30 |
+
|
31 |
+
|
32 |
+
## Citation
|
33 |
+
If you use this model, please cite the following paper:
|
34 |
+
```
|
35 |
+
@article{laki-yang-12lang,
|
36 |
+
title = {Solving Hungarian natural language processing tasks with multilingual generative models},
|
37 |
+
journal = {Annales Mathematicae et Informaticae},
|
38 |
+
year = {2023},
|
39 |
+
author = {Yang, Zijian Győző and Laki László János},
|
40 |
+
pages = {in press}
|
41 |
+
}
|
42 |
+
|
43 |
+
```
|