|
--- |
|
title: README |
|
emoji: ๐ |
|
colorFrom: red |
|
colorTo: gray |
|
sdk: static |
|
pinned: false |
|
--- |
|
|
|
# SeaLLMs - Large Language Models for Southeast Asia |
|
|
|
Welcome to the SeaLLMs project - a family of large language models tailored for Southeast Asian languages including English, Chinese, Indonesian, Vietnamese, Thai, Tagalog, Malay, Burmese, Khmer, Lao, Tamil, and Javanese. |
|
|
|
Unlike models primarily designed for high-resource languages like English, our mission is to democratize access to advanced language technologies for regional and potentially under-represented languages, |
|
while prioritizing safety and trustworthiness within the regional context. |
|
|
|
## โ๏ธ What's New (in 2025)? |
|
After the release of SeaLLMs-v3, we've focused on extending along two directions: language coverage and multimodal support. We are happy to share: |
|
|
|
- ๐ [Babel](https://babel-llm.github.io/babel-llm/): a multilingual LLM that covers the top 25 languages by number of speakers, supports over 90% of the global population |
|
- ๐ง [SeaLLMs-Audio](https://damo-nlp-sg.github.io/SeaLLMs-Audio/): the multimodal (audio) extension of SeaLLMs and the first large audio-language model designed to support multiple Southeast Asian languages |
|
|
|
## SeaLLMs Models |
|
|
|
- [SeaLLMs-v3](https://damo-nlp-sg.github.io/DAMO-SeaLLMs/): The latest version of the SeaLLMs family, achieving SOTA performance of diverse tasks while specifically enhanced to be more trustworthy, available in multiple variants: [7B-Chat](https://huggingface.co/SeaLLMs/SeaLLM3-7B-Chat), [1.5B-Chat](https://huggingface.co/SeaLLMs/SeaLLMs-v3-1.5B-Chat), [1.5B-base](https://huggingface.co/SeaLLMs/SeaLLMs-v3-1.5B) and [7B-base](https://huggingface.co/SeaLLMs/SeaLLMs-v3-7B). |
|
- [SeaLLMs/SeaLLM-7B-v2.5](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5): New SeaLLM-7B model with 7B-SOTA on many world knowledge and reasoning tasks in SEA languages. |
|
- [SeaLLMs/SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2): The most significant upgrade since SeaLLM-13B with half the size, outperforming performance across diverse multilingual tasks, from world knowledge, math reasoning, instruction following, etc. |
|
- [SeaLLMs/SeaLLM-13B-Chat](https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat): A chatbot optimized for Vietnamese ๐ป๐ณ, Indonesian ๐ฎ๐ฉ, Thai ๐น๐ญ, Malay ๐ฒ๐พ, Khmer๐ฐ๐ญ, Lao๐ฑ๐ฆ, Tagalog๐ต๐ญ and Burmese๐ฒ๐ฒ. |
|
|
|
## Multilingual Evaluations for SEA |
|
- [LLM Leaderboard for Southeast Asian Languages](https://huggingface.co/spaces/SeaLLMs/LLM_Leaderboard_for_SEA): evaluates LLMs on Southeast Asian languages through two comprehensive benchmarks - SeaExam and SeaBench |
|
- SeaExam assesses world knowledge and reasoning capabilities through exam-style questions (for both base and chat version models) [[data (public)](https://huggingface.co/datasets/SeaLLMs/SeaExam), [eval code](https://github.com/DAMO-NLP-SG/SeaExam)] |
|
- SeaBench evaluates instruction-following abilities and multi-turn conversational skills (thus only for chat version models). [[data (public)](https://huggingface.co/datasets/SeaLLMs/SeaBench), [eval code](https://github.com/DAMO-NLP-SG/SeaBench)] |
|
|
|
## Quick Links |
|
- [Project Page](https://damo-nlp-sg.github.io/DAMO-SeaLLMs/): project page that contains link to everything you need |
|
- [SeaLLM-Chatbot](https://huggingface.co/spaces/SeaLLMs/SeaLLM-Chat): online demo for the latest chatbot version of SeaLLMs (currently SeaLLMs-v3-7B-chat) |
|
- [SeaLLMs Github Repo](https://github.com/DAMO-NLP-SG/SeaLLMs) |
|
- [SeaLLMs Paper](https://arxiv.org/abs/2312.00738) (ACL 2024 Demo) |
|
- [SeaLLMs 3 Paper](https://arxiv.org/abs/2407.19672) (NAACL 2025 Demo) |