Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,59 @@
|
|
| 2 |
license: other
|
| 3 |
license_name: seallms
|
| 4 |
license_link: https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: other
|
| 3 |
license_name: seallms
|
| 4 |
license_link: https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
- zh
|
| 8 |
+
- vi
|
| 9 |
+
- id
|
| 10 |
+
- th
|
| 11 |
+
- ms
|
| 12 |
+
- km
|
| 13 |
+
- lo
|
| 14 |
+
- my
|
| 15 |
+
- tl
|
| 16 |
+
tags:
|
| 17 |
+
- multilingual
|
| 18 |
+
- sea
|
| 19 |
---
|
| 20 |
+
|
| 21 |
+
# *SeaLLM-7B-v2.5* - Large Language Models for Southeast Asia
|
| 22 |
+
|
| 23 |
+
<p align="center">
|
| 24 |
+
<a href="https://damo-nlp-sg.github.io/SeaLLMs/" target="_blank" rel="noopener">Technical Blog</a>
|
| 25 |
+
|
| 26 |
+
<a href="https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5" target="_blank" rel="noopener"> ๐ค Tech Memo</a>
|
| 27 |
+
|
| 28 |
+
<a href="https://huggingface.co/spaces/SeaLLMs/SeaLLM-7B" target="_blank" rel="noopener"> ๐ค DEMO</a>
|
| 29 |
+
|
| 30 |
+
<a href="https://github.com/DAMO-NLP-SG/SeaLLMs" target="_blank" rel="noopener">Github</a>
|
| 31 |
+
|
| 32 |
+
<a href="https://arxiv.org/pdf/2312.00738.pdf" target="_blank" rel="noopener">Technical Report</a>
|
| 33 |
+
</p>
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
We introduce [SeaLLM-7B-v2.5](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5), the state-of-the-art multilingual LLM for Southeast Asian (SEA) languagesย ๐ฌ๐ง ๐จ๐ณ ๐ป๐ณ ๐ฎ๐ฉ ๐น๐ญ ๐ฒ๐พ ๐ฐ๐ญ ๐ฑ๐ฆ ๐ฒ๐ฒ ๐ต๐ญ. It is the most significant upgrade since [SeaLLM-13B](https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat), with half the size, outperforming performance across diverse multilingual tasks, from world knowledge, math reasoning, instruction following, etc.
|
| 37 |
+
|
| 38 |
+
This is **Q4** quantized version for **MLX for apple silicon**. Checkout [SeaLLM-7B-v2.5 page](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5) for more details.
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
## Citation
|
| 42 |
+
|
| 43 |
+
If you find our project useful, we hope you would kindly star our repo and cite our work as follows: Corresponding Author: [l.bing@alibaba-inc.com](mailto:l.bing@alibaba-inc.com)
|
| 44 |
+
|
| 45 |
+
**Author list and order will change!**
|
| 46 |
+
|
| 47 |
+
* `*` and `^` are equal contributions.
|
| 48 |
+
|
| 49 |
+
```
|
| 50 |
+
@article{damonlpsg2023seallm,
|
| 51 |
+
author = {Xuan-Phi Nguyen*, Wenxuan Zhang*, Xin Li*, Mahani Aljunied*, Weiwen Xu, Hou Pong Chan,
|
| 52 |
+
Zhiqiang Hu, Chenhui Shen^, Yew Ken Chia^, Xingxuan Li, Jianyu Wang,
|
| 53 |
+
Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang,
|
| 54 |
+
Chaoqun Liu, Hang Zhang, Lidong Bing},
|
| 55 |
+
title = {SeaLLMs - Large Language Models for Southeast Asia},
|
| 56 |
+
year = 2023,
|
| 57 |
+
Eprint = {arXiv:2312.00738},
|
| 58 |
+
}
|
| 59 |
+
```
|
| 60 |
+
|