Comprehensive Thai-engineered model lineup from 1B to 70B parameters with 128K context and function-calling capabilities.
TYPHOON 2 features a comprehensive model lineup spanning from lightweight edge-optimized variants (1B and 3B parameters) to a powerful 70B parameter model, all specifically engineered for Thai language applications. The architecture demonstrates exceptional benchmark performance while supporting extensive context lengths up to 128,000 tokens, incorporating robust safety classification systems and sophisticated function-calling capabilities to enable advanced AI applications.