license: mit
Model Card for SEA LION
SEA LION is a collection of LLMs which has been pretrained and instruct-tuned for the Southeast Asia region. The models range from 3 billion to 7 billion parameters. This is the repository for the 3B pretrained model.
Model Details
Model Description
The SEA LION model is a significant leap forward in the field of natural language processing and understanding, specifically trained to understand South-East Asia (SEA) regional context. SEA LION stands for SouthEast Asian Languages In One Network. The SEA LION model comes in two variants, one with 3 billion parameters and another with 7 billion parameters. Both variants are built on the robust MPT architecture and utilize a vocabulary size of 256K. The model employs our proprietary SEABPETokenizer for tokenization. Our SEABPETokenizer is specially tailored for SEA languages, ensuring optimal model performance. The training data for SEA LION is encompasses 1 trillion tokens.
- Developed by: Products Pillar, AI Singapore
- Funded by [optional]: Singapore NRF
- Shared by [optional]: N/A
- Model type: Decoder
- Language(s) (NLP): English, Chinese, Indonesian, Malay, Thai, Vietnamese, Filipino, Tamil, Burmese, Khmer, Lao
- License: MIT License
- Finetuned from model [optional]: N/A
Model Sources [optional]
- Repository: Coming soon
- Paper [optional]: Coming soon
- Demo [optional]: Coming soon
Uses
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[ Todo: Insert Code Here ]
Training Details
Training Data
SEA LION 3B was trained on 980B tokens of the following data:
| Data Source | Tokens | Percentage |
|---|---|---|
| RefinedWeb - English | 571.3B | 62.80% |
| mC4 - Chinese | 91.2B | 10.03% |
| mC4 - Indonesian | 3.6B | 0.40% |
| mC4 - Malay | 0.7B | 0.08% |
| mC4 - Filipino | 1.3B | 0.15% |
| mC4 - Burmese | 1.2B | 0.13% |
| mC4 - Vietnamese | 63.4B | 6.97% |
| mC4 - Thai | 10.8B | 1.19% |
| mC4 - Lao | 0.3B | 0.03% |
| mC4 - Khmer | 0.9B | 0.11% |
| mC4 - Tamil | 2.5B | 0.28% |
| Python | 20.9B | 2.30% |
| Javascript | 55.6B | 6.11% |
| Shell | 1.3B | 0.14% |
| SQL | 6.4B | 0.70% |
| Markdown | 26.6B | 2.91% |
| StackExchange | 21.2B | 2.33% |
| ArXiv | 30.6B | 3.35% |
Training Procedure
SEA LION 3B was trained on 240 A100 40GB GPUs, using MosaicML Composer.
SEA LION 7B was trained on 256 A100 40GB GPUs, using MosaicML Composer.
Preprocessing [optional]
N/A
Training Hyperparameters
| Hyperparameter | Value |
|---|---|
| Precision | bfloat16 |
| Optimizer | decoupled_adamw |
| Scheduler | cosine_with_warmup |
| Learning Rate | 1.6e-4 |
| Global Batch Size | 1200 |
| Micro Batch Size | 5 |
Speeds, Sizes, Times [optional]
The training took 14 days to complete.
Evaluation
Testing Data, Factors & Metrics
Testing Data
Coming soon
Factors
Coming soon
Metrics
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA |
|---|---|---|---|---|---|
| SEA LION 3B | 40.35 | 36.26 | 64.60 | 24.07 | 36.47 |
| SEA LION 7B | 42.60 | 39.93 | 68.51 | 26.87 | 35.09 |
Results
Coming soon
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
SEA LION 3B is a decoder model using the MPT architecture.
| Parameter | Value |
|---|---|
| Layers | 40 |
| d_model | ? |
| head_dim | ? |
| Vocabulary | 256000 |
| Sequence Length | 2048 |
Compute Infrastructure
Hardware
SEA LION 3B was trained on AWS EC2 cluster comprising 30 p4d.24xlarge instances, using a total of 240 A100 40GB GPUs.
SEA LION 7B was trained on AWS EC2 cluster comprising 32 p4d.24xlarge instances, using a total of 256 A100 40GB GPUs.
Software
SEA LION 3B was trained using MosaicML Composer using PyTorch FullyShardedDataParallelism (FSDP).
Citation [optional]
BibTeX:
N/A
APA:
N/A
Glossary [optional]
N/A
More Information [optional]
N/A
The Team
Darius Liu
David Ong Tat-Wee
Hamsawardhini Rengarajan
Holy Lovenia
Lam Clarence
Leong Weiqi
Li Yier
Ng Raymond
Ngui Jian Gang
Railey Montalan
Tai Ngee Chia
Tan Choon Meng
Thanh Ngan Nguyen
Teo Jin Howe
Teo Wei Yi
William Tjhi
Yeo Yeow Tong
Yong Xianbin
Yosephine
Leslie Teo
Model Card Contact
For more info, please contact us at [email protected]