keisawada commited on
Commit
5400cdd
β€’
1 Parent(s): 2bb1278

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -1
README.md CHANGED
@@ -43,7 +43,7 @@ This repository provides a Japanese GPT-NeoX model of 3.6 billion parameters. Th
43
  | 3.6B SFT | https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft |
44
  | 3.6B pretrained | https://huggingface.co/rinna/japanese-gpt-neox-3.6b |
45
 
46
- * **Authors**
47
 
48
  [Tianyu Zhao](https://huggingface.co/tianyuz) and [Kei Sawada](https://huggingface.co/keisawada)
49
 
@@ -148,5 +148,23 @@ The model uses a [sentencepiece](https://github.com/google/sentencepiece)-based
148
  # 'გამარ[UNK]ობა 吾輩は ηŒ«γ§γ‚γ‚‹ </s>'
149
  ~~~
150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  # Licenese
152
  [The MIT license](https://opensource.org/licenses/MIT)
 
43
  | 3.6B SFT | https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft |
44
  | 3.6B pretrained | https://huggingface.co/rinna/japanese-gpt-neox-3.6b |
45
 
46
+ * **Contributors**
47
 
48
  [Tianyu Zhao](https://huggingface.co/tianyuz) and [Kei Sawada](https://huggingface.co/keisawada)
49
 
 
148
  # 'გამარ[UNK]ობა 吾輩は ηŒ«γ§γ‚γ‚‹ </s>'
149
  ~~~
150
 
151
+ # How to cite
152
+ ~~~
153
+ @misc{rinna-japanese-gpt-neox-3.6b-instruction-sft,
154
+ title = {rinna/japanese-gpt-neox-3.6b-instruction-sft},
155
+ author = {Zhao, Tianyu and Sawada, Kei}
156
+ url = {https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft},
157
+ }
158
+
159
+ @inproceedings{sawada2024release,
160
+ title = {Release of Pre-Trained Models for the {J}apanese Language},
161
+ author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
162
+ booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
163
+ month = {5},
164
+ year = {2024},
165
+ url = {https://arxiv.org/abs/2404.01657},
166
+ }
167
+ ~~~
168
+
169
  # Licenese
170
  [The MIT license](https://opensource.org/licenses/MIT)