Update README.md
Browse files
README.md
CHANGED
|
@@ -19,4 +19,30 @@ We use the **Traditional Mongolian texts** in MC^2 and **English texts** in RedP
|
|
| 19 |
* batch size: 1M (2K*512)
|
| 20 |
* lr scheduler: cosine
|
| 21 |
* min lr: 1e-6
|
| 22 |
-
* lr decay iters: 10240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
* batch size: 1M (2K*512)
|
| 20 |
* lr scheduler: cosine
|
| 21 |
* min lr: 1e-6
|
| 22 |
+
* lr decay iters: 10240
|
| 23 |
+
|
| 24 |
+
## Citation
|
| 25 |
+
If you find this model is useful in your work, please cite it with:
|
| 26 |
+
```
|
| 27 |
+
@inproceedings{tao-etal-2024-unlocking,
|
| 28 |
+
title = "Unlocking the Potential of Model Merging for Low-Resource Languages",
|
| 29 |
+
author = "Tao, Mingxu and
|
| 30 |
+
Zhang, Chen and
|
| 31 |
+
Huang, Quzhe and
|
| 32 |
+
Ma, Tianyao and
|
| 33 |
+
Huang, Songfang and
|
| 34 |
+
Zhao, Dongyan and
|
| 35 |
+
Feng, Yansong",
|
| 36 |
+
editor = "Al-Onaizan, Yaser and
|
| 37 |
+
Bansal, Mohit and
|
| 38 |
+
Chen, Yun-Nung",
|
| 39 |
+
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
|
| 40 |
+
month = nov,
|
| 41 |
+
year = "2024",
|
| 42 |
+
address = "Miami, Florida, USA",
|
| 43 |
+
publisher = "Association for Computational Linguistics",
|
| 44 |
+
url = "https://aclanthology.org/2024.findings-emnlp.508",
|
| 45 |
+
doi = "10.18653/v1/2024.findings-emnlp.508",
|
| 46 |
+
pages = "8705--8720"
|
| 47 |
+
}
|
| 48 |
+
```
|