DNA 2.1 is a fine-tuned Qwen3 14B model that thinks natively in Korean through a two-stage training approach. This model is released alongside the paper Making Qwen3 Think in Korean with Reinforcement Learning. — Two-Stage Training Approach: Supervised fine-tuning (SFT) on high-quality Korean reasoning datasets followed by reinforcement learning with our proposed Oracle-Guided Dr. GRPO algorithm — Native Korean Thinking: Conducts internal chain-of-thought reasoning entirely in Korean — Stable RL Training: Addresses reward hacking and policy collapse through oracle judge model for reward signal calibration — Enhanced Reasoning Performance: Substantially improved results on advanced reasoning benchmarks, particularly in math and coding tasks — Preserved Knowledge & Language Proficiency: Maintains existing knowledge and language capabilities after reinfor If you use this model in your research, please cite our paper:
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: dnotitia
Теги: qwen3, conversational, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 39
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
