SEA-LION

A family of open-source large language models tuned to better understand Southeast Asia's diverse languages and cultures, developed by AI Singapore's Products Pillar.

Models

Visit website sea-lion.ai

SEA-LION, short for Southeast Asian Languages in One Network, targets under-represented population groups and low-resource languages in the Southeast Asian region. Its releases span from small pre-trained-from-scratch models to large continued-pretrained and supervised-fine-tuned models built on bases such as Llama, Gemma, Qwen and NVIDIA Nemotron, up to a 120-billion-parameter mixture-of-experts model with 128K context.

Models are distributed in base, instruct, vision-language, reasoning and GGUF-quantized variants, along with a separate SEA-LION embedding model. The project's site documents how to access the models, hosting options and how-to guides for the SEA-LION family.

More in Models

See all 405

mini-AGI
github.com
A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.
- Models
Applied Inference Lab: Compliance Control Embedding Stack
github.com
An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.
- Models
- Security
peekaboolean
github.com
A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.
- Models
- Inference

More in Models

mini-AGI

Applied Inference Lab: Compliance Control Embedding Stack

peekaboolean

Cookies