按年被提到
20222023 · 1 次2026
大模型与语言模型›长上下文与测试时计算·arXiv:2212.10544 · cs.CL

Pretraining Without Attention

Junxiong Wang, Jing Nathan Yan, Albert Gu, Alexander M. Rush · 2022
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-05-10 · 最近 2024-04-30
2不同的人
2活跃月份
2讨论串
16被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Transformers have been essential to pretraining success in NLP. While other architectures have been used, downstream accuracy is either significantly worse, or requires attention layers to match standard benchmarks such as GLUE. This work explores pretraining without attention by using recent advances in sequence routing based on state-space models (SSMs). Our proposed model, Bidirectional Gated SSM (BiGS), combines SSM layers with a multiplicative gating architecture that has been effective in simplified sequence modeling architectures. The model learns static layers that do not consider pair-wise interactions. Even so, BiGS is able to match BERT pretraining accuracy on GLUE and can be extended to long-form pretraining of 4096 tokens without approximation. Analysis shows that while the models have similar average accuracy, the approach has different inductive biases than BERT in terms of interactions and syntactic representations. All models from this work are available at https://github.com/jxiw/BiGS.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 2 次