Старшая версия в линейке Typhoon, сочетающая мощь 12 миллиардов параметров и продвинутые методы обучения с подкреплением. Эта ИИ-модель демонстрирует высокую точность в генерации кода и сложных рассуждениях, сохраняя фокус на тайском языке. Благодаря огромному контекстному окну, она легко справляется с обработкой объемных документов.
Typhoon2.1-Gemma3-12B is a instruct Thai 🇹🇭 large language model with 12 billion parameters, a 128K context length, and function-calling capabilities. It is based on Gemma3 12B. To build Typhoon 2.1 (Gemma3-based), we introduced a new approach that combines fine-tuning, model merging techniques from Typhoon 2 R1, and reinforcement learning (RL) fine-tuning—details to be shared in an upcoming paper. We began by using supervised fine-tuning (SFT) and merging to align the model with Thai-specific preferences, applying a curated subset of post-training recipes from Typhoon 2. This made the model more controllable and better suited to Thai use cases. Once we achieved strong instruction-following in Thai, we applied RL fine-tuning to correct merging artifacts and train the model to perform controllable long-thought processes.