SeaLLMs - Large Language Models for Southeast Asia

Welcome to the Huggingface organization that hosts SeaLLMs - a family of language models optimized for Southeast Asian languages. Rather than being focused on English and alike, we believe language models should be democratized to other regional and possibly under-represented languages, and adapted to serve communities there with a greater awareness of local norms and laws.

SeaLLMs Models

• 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: 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: A chatbot optimized for Vietnamese 🇻🇳, Indonesian 🇮🇩, Thai 🇹🇭, Malay 🇲🇾, Khmer🇰🇭, Lao🇱🇦, Tagalog🇵🇭 and Burmese🇲🇲.
• SeaLLMs/Sea-bench (interactive view at Spaces/SeaLLMs/Sea-bench): A benchmark for evaluating chat assistants in Southeast Asian languages.

DEMO

• spaces/SeaLLMs/SeaLLM-7B-v2.5.
• spaces/SeaLLMs/SeaLLM-7B-v2.
• spaces/SeaLLMs/SeaLLM-7B - Multimodal SeaLLM (experimental)