Oleksii Kuchaiev
@kuchaev
Director, AI model post-training @NVIDIA
ID: 116043858
http://www.kuchaev.com 20-02-2010 23:26:09
651 Tweet
1,1K Takipçi
880 Takip Edilen
Teknium (e/λ) This is a "runtime" feature. We started with same approach as Qwen3 but noticed that the model starts "thinking" outside of the thinking trace of forced to answer. Training on truncated thinking traces fixed that. Section 3.4 research.nvidia.com/labs/adlr/file…