Update README.md
#2
by
AndrewZeng
- opened
README.md
CHANGED
@@ -97,3 +97,18 @@ The following hyperparameters were used during training:
|
|
97 |
- Pytorch 2.1.0+cu121
|
98 |
- Datasets 2.14.6
|
99 |
- Tokenizers 0.14.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
- Pytorch 2.1.0+cu121
|
98 |
- Datasets 2.14.6
|
99 |
- Tokenizers 0.14.1
|
100 |
+
|
101 |
+
|
102 |
+
## Citation
|
103 |
+
If you find the content of this project helpful, please cite our paper as follows:
|
104 |
+
|
105 |
+
```
|
106 |
+
@misc{liu2023what,
|
107 |
+
title={What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning},
|
108 |
+
author={Wei Liu and Weihao Zeng and Keqing He and Yong Jiang and Junxian He},
|
109 |
+
year={2023},
|
110 |
+
eprint={2312.15685},
|
111 |
+
archivePrefix={arXiv},
|
112 |
+
primaryClass={cs.CL}
|
113 |
+
}
|
114 |
+
```
|