Update README.md
Browse files
README.md
CHANGED
@@ -205,8 +205,23 @@ llm-jp(at)nii.ac.jp
|
|
205 |
|
206 |
[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
207 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
208 |
## Model Card Authors
|
209 |
|
210 |
*The names are listed in alphabetical order.*
|
211 |
|
212 |
-
Hirokazu Kiyomaru and
|
|
|
205 |
|
206 |
[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
207 |
|
208 |
+
## How to cite
|
209 |
+
|
210 |
+
If you find our work helpful, please feel free to cite the paper.
|
211 |
+
|
212 |
+
```
|
213 |
+
@inproceedings{
|
214 |
+
nakamura2025dropupcycling,
|
215 |
+
title={Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization},
|
216 |
+
author={Taishi Nakamura and Takuya Akiba and Kazuki Fujii and Yusuke Oda and Rio Yokota and Jun Suzuki},
|
217 |
+
booktitle={The Thirteenth International Conference on Learning Representations},
|
218 |
+
year={2025},
|
219 |
+
url={https://openreview.net/forum?id=gx1wHnf5Vp}
|
220 |
+
}
|
221 |
+
```
|
222 |
+
|
223 |
## Model Card Authors
|
224 |
|
225 |
*The names are listed in alphabetical order.*
|
226 |
|
227 |
+
Hirokazu Kiyomaru, Takashi Kodama and Taishi Nakamura.
|