AI 精选动态
智能评分 60
Nemotron-Labs-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context
AI 推荐理由
该工作展示了将预训练自回归模型拆分为双塔进行扩散生成的新方法，无需额外训练即可显著加速，值得关注其技术细节和适用性。核心解读
NVIDIA Research 发布 Nemotron-Labs-TwoTower 扩散语言模型，将 30B 参数的 Nemotron-3-Nano-30B-A3B 模型拆分为两半并行生成 token，无需从头训练。实验表明，该方法保留了原始模型 98.7% 的质量，生成速度提升 2.42 倍。
全文
Nemotron-Labs-TwoTower:
Diffusion Language Modeling with Pretrained Autoregressive Context
> **引用原帖 NVIDIA AI (@NVIDIAAI):**
> We took a 30B model and split it in two to write tokens in parallel instead of one at a time.
> Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch.
> We found it kept 98.7% of the original model’s quality at 2.42× faster generation.
> https://x.com/NVIDIAAI/status/2072394812301480067