Yiran0924 commited on
Commit
6bcadea
•
1 Parent(s): 8491f0c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -20,13 +20,16 @@ tags:
20
  <p align="center">
21
  <a href="https://damo-nlp-sg.github.io/SeaLLMs/" target="_blank" rel="noopener">Website</a>
22
  &nbsp;&nbsp;
23
- <a href="https://huggingface.co/SeaLLMs/SeaLLMs-v3-7B" target="_blank" rel="noopener"> 🤗 Tech Memo</a>
 
 
24
  &nbsp;&nbsp;
25
  <a href="https://github.com/DAMO-NLP-SG/SeaLLMs" target="_blank" rel="noopener">Github</a>
26
  &nbsp;&nbsp;
27
  <a href="https://arxiv.org/pdf/2312.00738.pdf" target="_blank" rel="noopener">Technical Report</a>
28
  </p>
29
 
 
30
  We introduce **SeaLLMs-v3**, the latest series of the SeaLLMs (Large Language Models for Southeast Asian languages) family. It achieves state-of-the-art performance among models with similar sizes, excelling across a diverse array of tasks such as world knowledge, mathematical reasoning, translation, and instruction following. In the meantime, it was specifically enhanced to be more trustworthy, exhibiting reduced hallucination and providing safe responses, particularly in queries closed related to Southeast Asian culture.
31
 
32
  ## 🔥 Highlights
 
20
  <p align="center">
21
  <a href="https://damo-nlp-sg.github.io/SeaLLMs/" target="_blank" rel="noopener">Website</a>
22
  &nbsp;&nbsp;
23
+ <a href="https://huggingface.co/SeaLLMs/SeaLLMs-v3-1.5B-Chat" target="_blank" rel="noopener"> 🤗 Tech Memo</a>
24
+ &nbsp;&nbsp;
25
+ <a href="https://huggingface.co/spaces/SeaLLMs/SeaLLM-Chat" target="_blank" rel="noopener"> 🤗 DEMO</a>
26
  &nbsp;&nbsp;
27
  <a href="https://github.com/DAMO-NLP-SG/SeaLLMs" target="_blank" rel="noopener">Github</a>
28
  &nbsp;&nbsp;
29
  <a href="https://arxiv.org/pdf/2312.00738.pdf" target="_blank" rel="noopener">Technical Report</a>
30
  </p>
31
 
32
+
33
  We introduce **SeaLLMs-v3**, the latest series of the SeaLLMs (Large Language Models for Southeast Asian languages) family. It achieves state-of-the-art performance among models with similar sizes, excelling across a diverse array of tasks such as world knowledge, mathematical reasoning, translation, and instruction following. In the meantime, it was specifically enhanced to be more trustworthy, exhibiting reduced hallucination and providing safe responses, particularly in queries closed related to Southeast Asian culture.
34
 
35
  ## 🔥 Highlights