anocha-mcomp commited on
Commit
ca09a06
·
verified ·
1 Parent(s): 4d01f76

Update model card from Confluence: Model Card: Apertus-SEA-LION-v4-8B-IT

Browse files
model_card_apertus-sea-lion-v4-8b-it.md CHANGED
@@ -4,15 +4,15 @@
4
 
5
  SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
6
 
7
- **Apertus-SEA-LION-v4-8B-IT** is a 8-billion parameter model built upon the Apertus-8B-Instruct architecture. To ensure **domain adaptation** for the region, the model underwent rigorous post-training on a curated dataset of approximately 8.54 **million** instruction-text pairs.
8
 
9
- This extensive post-training instills **multilingual** and **multicultural** fluency, covering key SEA languages such as Burmese, Malay, Tagalog and Tamil. The dataset also includes 347, 000 tool-calling instruction-text pairs to impart these capabilities, in addition to linguistic fluency.
10
 
11
  Apertus-SEA-LION-v4-8B-IT is designed as a fully open model; to align with this core philosophy, we have released the datasets used for post-training, as well as the evaluation codes and datasets used to evaluate the model.
12
 
13
  These resources can be accessed via the link below.
14
 
15
- - [Open post-training dataset](https://aisg-products.atlassian.net/wiki/spaces/SEALION/pages/1115553805/Model+Card+Apertus-SEA-LION-v4-8B-IT#Training-Data)s we used.
16
  - [SEA-HELM Evaluation codes and datasets](<https://github.com/aisingapore/SEA-HELM>)
17
 
18
  ## Model Details
 
4
 
5
  SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
6
 
7
+ **Apertus-SEA-LION-v4-8B-IT** is a 8-billion parameter model built upon the Apertus-8B-Instruct architecture. To ensure **domain adaptation** for the region, the model underwent rigorous post-training on a curated dataset of approximately **8.54 million** instruction-text pairs.
8
 
9
+ This extensive post-training instills **multilingual** and **multicultural** fluency, covering key SEA languages such as Burmese, Malay, Tagalog and Tamil. The dataset also includes 347,000 tool-calling instruction-text pairs to impart these capabilities, in addition to linguistic fluency.
10
 
11
  Apertus-SEA-LION-v4-8B-IT is designed as a fully open model; to align with this core philosophy, we have released the datasets used for post-training, as well as the evaluation codes and datasets used to evaluate the model.
12
 
13
  These resources can be accessed via the link below.
14
 
15
+ - [Open post-training datasets](https://aisg-products.atlassian.net/wiki/spaces/SEALION/pages/1115553805/Model+Card+Apertus-SEA-LION-v4-8B-IT#Training-Data) we used.
16
  - [SEA-HELM Evaluation codes and datasets](<https://github.com/aisingapore/SEA-HELM>)
17
 
18
  ## Model Details