Что объясняет эта страница
Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...
- Deepcogito · deepcogito/cogito-v2.1-671b
- text->text · глобальный маршрут модели
- 128 000 context · 1,25 $ input