Update README.md
Browse files
README.md
CHANGED
@@ -2,27 +2,35 @@
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
|
5 |
-
# Model Card for
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
-
|
9 |
-
|
|
|
10 |
|
11 |
## Model Details
|
12 |
|
13 |
### Model Description
|
14 |
|
15 |
<!-- Provide a longer summary of what this model is. -->
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
- **Shared by [optional]:** [More Information Needed]
|
22 |
- **Model type:** [More Information Needed]
|
23 |
-
- **Language(s) (NLP):**
|
24 |
-
- **License:**
|
25 |
-
- **Finetuned from model [optional]:**
|
26 |
|
27 |
### Model Sources [optional]
|
28 |
|
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
|
5 |
+
# Model Card for SEA LION
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
+
SEA LION is a collection of LLMs which has been pretrained and instruct-tuned for the Southeast Asia region.
|
9 |
+
The models range from 3 billion to 7 billion parameters.
|
10 |
+
This is the repository for the 3B pretrained model.
|
11 |
|
12 |
## Model Details
|
13 |
|
14 |
### Model Description
|
15 |
|
16 |
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
The SEA LION model is a significant leap forward in the field of natural language processing and understanding,
|
18 |
+
specifically trained to understand South-East Asia (SEA) regional context.
|
19 |
+
SEA LION stands for SouthEast Asian Languages In One Network.
|
20 |
+
The SEA LION model comes in two variants, one with 3 billion parameters and another with 7 billion parameters.
|
21 |
+
Both variants are built on the robust MPT architecture and utilize a vocabulary size of 256K.
|
22 |
+
The model employs our proprietary SEABPETokenizer for tokenization.
|
23 |
+
Our SEABPETokenizer is specially tailored for SEA languages, ensuring optimal model performance.
|
24 |
+
The training data for SEA LION is encompasses 1 trillion tokens.
|
25 |
+
|
26 |
+
|
27 |
+
- **Developed by:** Products Pillar, AI Singapore
|
28 |
+
- **Funded by [optional]:** Singapore NRF
|
29 |
- **Shared by [optional]:** [More Information Needed]
|
30 |
- **Model type:** [More Information Needed]
|
31 |
+
- **Language(s) (NLP):** English, Chinese, Indonesian, Malay, Thai, Vietnamese, Filipino/Tagalog, Tamil, Burnese, Khmer, Lao
|
32 |
+
- **License:** Apache 2.0
|
33 |
+
- **Finetuned from model [optional]:** N/A
|
34 |
|
35 |
### Model Sources [optional]
|
36 |
|