gabrielchua commited on
Commit
67849a3
·
verified ·
1 Parent(s): d02534e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -3
README.md CHANGED
@@ -1,9 +1,11 @@
1
  ---
2
  base_model:
3
- - aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct
4
  language:
5
  - en
6
  license: llama3
 
 
7
  ---
8
  # Llama3 8B SEA-Lionv2.1 SECURE
9
  Llama3 8B SEA-Lionv2.1 SECURE is built upon Llama3 8B CPT SEA-Lionv2.1 Instruct, a variant of Llama-3-8B-Instruct fine-tuned for ASEAN languages. While the base model enhances multilingual capabilities, it lacks dedicated safety alignment for Singlish. Llama3 8B SEA-Lionv2.1 SECURE specifically addresses this gap by incorporating targeted safety alignment to mitigate Singlish-related toxicity, ensuring safer responses in Singlish-speaking contexts.
@@ -83,5 +85,4 @@ Isaac Lim, Shaun Khoo, Goh Jiayi, Jessica Foo, Watson Chua
83
  For more information, please reach out to [email protected].
84
 
85
  ## Acknowledgements
86
- Acknowledgments for contributors and supporting teams will be added soon.
87
-
 
1
  ---
2
  base_model:
3
+ - aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct
4
  language:
5
  - en
6
  license: llama3
7
+ pipeline_tag: text-generation
8
+ library_name: transformers
9
  ---
10
  # Llama3 8B SEA-Lionv2.1 SECURE
11
  Llama3 8B SEA-Lionv2.1 SECURE is built upon Llama3 8B CPT SEA-Lionv2.1 Instruct, a variant of Llama-3-8B-Instruct fine-tuned for ASEAN languages. While the base model enhances multilingual capabilities, it lacks dedicated safety alignment for Singlish. Llama3 8B SEA-Lionv2.1 SECURE specifically addresses this gap by incorporating targeted safety alignment to mitigate Singlish-related toxicity, ensuring safer responses in Singlish-speaking contexts.
 
85
  For more information, please reach out to [email protected].
86
 
87
  ## Acknowledgements
88
+ Acknowledgments for contributors and supporting teams will be added soon.