multilingual
sea
nxphi47 commited on
Commit
c694d50
ยท
1 Parent(s): 87f5c24

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -10,11 +10,11 @@ inference: false
10
 
11
 
12
  <p align="center">
13
- <a href="https://huggingface.co/SeaLLMs/SeaLLM-Chat-13b-internal" target="_blank"> ๐Ÿค— Tech Memo</a>
14
  &nbsp;&nbsp;
15
- <a href="https://huggingface.co/spaces/SeaLLMs/SeaLLM-Chat-13b" target="_blank"> ๐Ÿค— DEMO</a>
16
  &nbsp;&nbsp;
17
- <a href="https://github.com/SeaLLMs/SeaLLMs" target="_blank">Github</a>
18
  </p>
19
 
20
  We introduce SeaLLM - a family of language models optimized for Southeast Asian (SEA) languages. The SeaLLM-base models (to be released) were pre-trained from [Llama-2](https://huggingface.co/meta-llama/Llama-2-13b-hf), on a tailored publicly-available dataset, which comprises mainly Vietnamese ๐Ÿ‡ป๐Ÿ‡ณ, Indonesian ๐Ÿ‡ฎ๐Ÿ‡ฉ and Thai ๐Ÿ‡น๐Ÿ‡ญ texts, along with those in English ๐Ÿ‡ฌ๐Ÿ‡ง and Chinese ๐Ÿ‡จ๐Ÿ‡ณ. The pre-training stage involves multiple stages with dynamic data control to preserve the original knowledge base of Llama-2 while gaining new abilities in SEA languages.
 
10
 
11
 
12
  <p align="center">
13
+ <a href="https://huggingface.co/SeaLLMs/SeaLLM-Chat-13b" target="_blank" rel="noopener"> ๐Ÿค— Tech Memo</a>
14
  &nbsp;&nbsp;
15
+ <a href="https://huggingface.co/spaces/SeaLLMs/SeaLLM-Chat-13b" target="_blank" rel="noopener"> ๐Ÿค— DEMO</a>
16
  &nbsp;&nbsp;
17
+ <a href="https://github.com/SeaLLMs/SeaLLMs" target="_blank" rel="noopener">Github</a>
18
  </p>
19
 
20
  We introduce SeaLLM - a family of language models optimized for Southeast Asian (SEA) languages. The SeaLLM-base models (to be released) were pre-trained from [Llama-2](https://huggingface.co/meta-llama/Llama-2-13b-hf), on a tailored publicly-available dataset, which comprises mainly Vietnamese ๐Ÿ‡ป๐Ÿ‡ณ, Indonesian ๐Ÿ‡ฎ๐Ÿ‡ฉ and Thai ๐Ÿ‡น๐Ÿ‡ญ texts, along with those in English ๐Ÿ‡ฌ๐Ÿ‡ง and Chinese ๐Ÿ‡จ๐Ÿ‡ณ. The pre-training stage involves multiple stages with dynamic data control to preserve the original knowledge base of Llama-2 while gaining new abilities in SEA languages.