Commit
•
7c150ca
1
Parent(s):
c4aca12
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -48,3 +48,17 @@ tokenizer = AutoTokenizer.from_pretrained(
|
|
| 48 |
```
|
| 49 |
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
```
|
| 49 |
|
| 50 |
|
| 51 |
+
## Citation
|
| 52 |
+
```
|
| 53 |
+
@article{yamaguchi-etal-2024-effectively,
|
| 54 |
+
title={How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?},
|
| 55 |
+
author={Atsuki Yamaguchi and Aline Villavicencio and Nikolaos Aletras},
|
| 56 |
+
year={2024},
|
| 57 |
+
journal={ArXiv},
|
| 58 |
+
year={2024},
|
| 59 |
+
volume={abs/2406.11477},
|
| 60 |
+
url={https://arxiv.org/abs/2406.11477},
|
| 61 |
+
}
|
| 62 |
+
```
|
| 63 |
+
|
| 64 |
+
|