Update README.md
Browse files
README.md
CHANGED
@@ -2,8 +2,6 @@
|
|
2 |
language: ja
|
3 |
thumbnail: https://github.com/rinnakk/japanese-gpt2/blob/master/rinna.png
|
4 |
tags:
|
5 |
-
- ja
|
6 |
-
- japanese
|
7 |
- gpt2
|
8 |
- text-generation
|
9 |
- lm
|
@@ -43,11 +41,11 @@ The model was trained on [Japanese CC-100](http://data.statmt.org/cc-100/ja.txt.
|
|
43 |
The model uses a [sentencepiece](https://github.com/google/sentencepiece)-based tokenizer, the vocabulary was trained on the Japanese Wikipedia using the official sentencepiece training script.
|
44 |
|
45 |
# How to cite
|
46 |
-
|
47 |
@misc{rinna-japanese-gpt2-xsmall,
|
48 |
title = {rinna/japanese-gpt2-xsmall},
|
49 |
-
author = {Zhao, Tianyu and Sawada, Kei}
|
50 |
-
url = {https://huggingface.co/rinna/japanese-gpt2-xsmall}
|
51 |
}
|
52 |
|
53 |
@inproceedings{sawada2024release,
|
@@ -56,9 +54,11 @@ The model uses a [sentencepiece](https://github.com/google/sentencepiece)-based
|
|
56 |
booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
|
57 |
month = {5},
|
58 |
year = {2024},
|
59 |
-
|
|
|
|
|
60 |
}
|
61 |
-
|
62 |
|
63 |
# Licenese
|
64 |
[The MIT license](https://opensource.org/licenses/MIT)
|
|
|
2 |
language: ja
|
3 |
thumbnail: https://github.com/rinnakk/japanese-gpt2/blob/master/rinna.png
|
4 |
tags:
|
|
|
|
|
5 |
- gpt2
|
6 |
- text-generation
|
7 |
- lm
|
|
|
41 |
The model uses a [sentencepiece](https://github.com/google/sentencepiece)-based tokenizer, the vocabulary was trained on the Japanese Wikipedia using the official sentencepiece training script.
|
42 |
|
43 |
# How to cite
|
44 |
+
```bibtex
|
45 |
@misc{rinna-japanese-gpt2-xsmall,
|
46 |
title = {rinna/japanese-gpt2-xsmall},
|
47 |
+
author = {Zhao, Tianyu and Sawada, Kei},
|
48 |
+
url = {https://huggingface.co/rinna/japanese-gpt2-xsmall}
|
49 |
}
|
50 |
|
51 |
@inproceedings{sawada2024release,
|
|
|
54 |
booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
|
55 |
month = {5},
|
56 |
year = {2024},
|
57 |
+
pages = {13898--13905},
|
58 |
+
url = {https://aclanthology.org/2024.lrec-main.1213},
|
59 |
+
note = {\url{https://arxiv.org/abs/2404.01657}}
|
60 |
}
|
61 |
+
```
|
62 |
|
63 |
# Licenese
|
64 |
[The MIT license](https://opensource.org/licenses/MIT)
|