DeepSeek-V3.2, every mention
2 scenes · ← back to DeepSeek-V3.2
tap a year for its mentions
every year anyone Sebastian Raschka 2
Verbatim, from the transcripts: the passages where DeepSeek-V3.2 comes up
State of LLMs 2026: RLVR, GRPO, Inference Scaling — Sebastian Raschka
- ▶ 16:21 Sebastian Raschka Uh, DeepSig version 3.2, where they changed attention mechanism.
- ▶ 37:29 Sebastian Raschka I mean, if you look at a version three and then R one, and then they had version 3.2 model with the sparse attention mechanism, and then also this math version two with a self refinement and everything.