# SEA-LION Foundation Family The SEA-LION models have served as a foundation for developing localized AI solutions tailored to specific linguistic and cultural needs. Over multiple iterations, other regions have built upon SEA-LION’s architecture to create specialized versions that enhance language understanding for their respective regions. These models leverage SEA-LION’s robust multilingual capabilities while being fine-tuned with localized datasets, ensuring better performance in regional contexts. ## SEA-LION Model Tree

Base	Localized Model
SEA-LION v1	→ WangchanLion 7B (Thai): WangchanLion 7B is a multilingual instruction-following model developed by PyThaiNLP and the VISTEC-depa AI Research Institute of Thailand. Fine-tuned on SEA-LION-v1-7B, it incorporates approximately 500,000 samples from open-source, commercially permissible datasets, with a focus on Thai and English languages.
SEA-LION v2	→ Llama3 8B CPT Sahabat-AI v1 Instruct (Indonesian): Llama3 8B CPT Sahabat-AI v1 Instruct model, co-developed by GoTo Group and AI Singapore, is an Indonesian-focused adaptation fine-tuned with 448,000 Indonesian instruction-completion pairs, along with 96,000 Javanese and 98,000 Sundanese pairs. It supports Indonesian, Javanese, Sundanese, and English, making it a significant advancement in AI for the Indonesian linguistic landscape.
SEA-LION v3	→ Gemma2 9B WangchanLIONv2 (Thai): The Gemma2 9B WangchanLIONv2 Instruct model is a collaborative effort between VISTEC and AI Singapore. It has been fine-tuned with approximately 3,760,000 Thai instruction-completion pairs derived from human-annotated instructions, FLAN-style automatic data construction, and synthetic samples. This multilingual model supports both Thai and English languages. → Gemma2 9B CPT Sahabat-AI (Indonesian): The Gemma2 9B CPT Sahabat-AI v1 Instruct model, co-developed by GoTo Group and AI Singapore, has been fine-tuned with approximately 448,000 Indonesian instruction-completion pairs, along with 96,000 in Javanese, 98,000 in Sundanese, and an additional 129,000 in English. This multilingual model supports Indonesian, Javanese, Sundanese, and English.
SEA-LION v4	→ Gemma 3 27B/4B SEA-LION v4 (Multimodal): The first multimodal release in the SEA-LION family, based on the Gemma 3 architecture. Co-developed with Google, these models support a 128K context window. It underwent post-training on ~10M samples across 11 SEA languages and features vision-text capabilities for document understanding and visual Q&A. This model supports text and image understanding with a commercially permissive license. It is designed to handle Southeast Asian cultural nuances and visual contexts. → Qwen-SEA-LION-v4-4B/8B-IT: The lightweight flagship multimodal model built on the Qwen3-VL framework, optimized for regional linguistic and cultural nuances. → Apertus 8B SEA-LION v4: A fully open regional adaptation based on the Swiss AI "Apertus" architecture, focusing on highly efficient, transparent, and community-driven multilingual support. Features 15T token pre-training across 1,000+ languages with a focus on deep multilingual depth and transparency.
SEA-Guard	A specialized collection of safety-focused LLMs built on the SEA-LION family released on 4 Feb 2026. → Qwen-SEA-Guard-4B/8B (Image-to-Text): The 4B variant is a lightweight visual guardrail optimized for edge applications, while the 8B offers balanced visual moderation with stronger reasoning capabilities. → Llama-SEA-Guard-8B (Text Generation): A text-only safety specialist optimized for chat moderation and policy enforcement, ensuring safe interactions in dialogue systems. → Gemma-SEA-Guard-12B (Multimodal): The high-capacity safety flagship capable of interpreting complex relationships between visual and textual data for deep content analysis.
SEA-LION Embedding	A suite of high-performance encoder-only models specifically architected for Southeast Asian languages, providing state-of-the-art vector representations for RAG and semantic search. → SEA-LION-ModernBERT-Embedding (Encoder): Our flagship encoder line utilizing the ModernBERT architecture. It offers superior efficiency and long-context handling, specifically tuned for the unique scripts and linguistic structures of the SEA region. → SEA-LION-E5-Embedding (Encoder): A high-precision semantic encoder line fine-tuned from the E5-large foundation, optimized for maximum accuracy in cross-lingual retrieval and semantic matching across regional and global languages.

## Impact and Future Directions By leveraging SEA-LION’s architecture, these localized models provide AI solutions that align more closely with native language requirements. As SEA-LION continues to evolve, more localized versions are expected to emerge, further expanding the reach and effectiveness of AI in Southeast Asian languages.