你即將離開本站

並前往https://arxiv.org/abs/2108.09084

Fastformer: Additive Attention Can Be All You Need - arXiv

由 C Wu 著作 · 2021 · 被引用 7 次 — Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length.

確定！ 回上一頁

查詢 「Fast transformer」的人也找了：

  1. BertForSequenceClassification PyTorch
    2.
  2. Performer GitHub
    3.
  3. Linear transformer
    4.
  4. Fast transformer mask
    5.
  5. Faster Transformer
    6.
  6. Autoregressive transformer
    7.
  7. Fastformer: Additive Attention Can Be All You Need
    8.
  8. Reformer: THE efficient Transformer
    9.