korrents

transformers

The architecture that dropped recurrence in favour of attention, and that almost every large model since is built on.

What people on korrents have said about transformers, newest first — 25 positions from 9 people.

FilterEveryone, all time
Who Everyone AGAidan N. Gomez 3 AVAshish Vaswani 3 IPIllia Polosukhin 3 JUJakob Uszkoreit 3 LJLlion Jones 3 ŁKŁukasz Kaiser 3 NPNiki Parmar 3 NSNoam Shazeer 3 DHDex Horthy 1
When All time Past 1 yearPast 3 yearsPast 5 years
  1. DH

    Dex Horthy quoted

    Our readingContext engineering has stayed relevant for a year because it is grounded in how transformer attention works, and it will matter to anyone building on AI until post-transformer models arrive.

    Their wordsI think context engineering has been so long lived because it's it's grounded in the fundamentals of how transformer attention works and until we have post transformer models or linear attention or whatever it is which who knows when that's going to happen context engineering will be interesting and important to anyone building on AI

    ↗Context engineering with Dex Horthyyoutube.com 3rd of 26 in this recording

  2. 9 years earlier
  3. AV

    Ashish Vaswani quoted

    Our readingSequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    ↗Attention is all you needarxiv.org 1st of 24 in this piece

  5. NS

    Noam Shazeer quoted

    Our readingSequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    ↗Attention is all you needarxiv.org 2nd of 24 in this piece

  7. NP

    Niki Parmar quoted

    Our readingSequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    ↗Attention is all you needarxiv.org 3rd of 24 in this piece

  9. JU

    Jakob Uszkoreit quoted

    Our readingSequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    ↗Attention is all you needarxiv.org 4th of 24 in this piece

  11. LJ

    Llion Jones quoted

    Our readingSequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    ↗Attention is all you needarxiv.org 5th of 24 in this piece

  13. AG

    Aidan N. Gomez quoted

    Our readingSequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    ↗Attention is all you needarxiv.org 6th of 24 in this piece

  15. ŁK

    Łukasz Kaiser quoted

    Our readingSequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    ↗Attention is all you needarxiv.org 7th of 24 in this piece

  17. IP

    Illia Polosukhin quoted

    Our readingSequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    ↗Attention is all you needarxiv.org 8th of 24 in this piece

  19. AV

    Ashish Vaswani quoted

    Our readingA transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    ↗Attention is all you needarxiv.org 9th of 24 in this piece

  21. NS

    Noam Shazeer quoted

    Our readingA transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    ↗Attention is all you needarxiv.org 10th of 24 in this piece

  23. NP

    Niki Parmar quoted

    Our readingA transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    ↗Attention is all you needarxiv.org 11th of 24 in this piece

  25. JU

    Jakob Uszkoreit quoted

    Our readingA transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    ↗Attention is all you needarxiv.org 12th of 24 in this piece

  27. LJ

    Llion Jones quoted

    Our readingA transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    ↗Attention is all you needarxiv.org 13th of 24 in this piece

  29. AG

    Aidan N. Gomez quoted

    Our readingA transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    ↗Attention is all you needarxiv.org 14th of 24 in this piece

  31. ŁK

    Łukasz Kaiser quoted

    Our readingA transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    ↗Attention is all you needarxiv.org 15th of 24 in this piece

  33. IP

    Illia Polosukhin quoted

    Our readingA transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    ↗Attention is all you needarxiv.org 16th of 24 in this piece

  35. AV

    Ashish Vaswani quoted

    Our readingSelf-attention can yield more interpretable models.

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    ↗Attention is all you needarxiv.org 17th of 24 in this piece

  37. NS

    Noam Shazeer quoted

    Our readingSelf-attention can yield more interpretable models.

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    ↗Attention is all you needarxiv.org 18th of 24 in this piece

  39. NP

    Niki Parmar quoted

    Our readingSelf-attention can yield more interpretable models.

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    ↗Attention is all you needarxiv.org 19th of 24 in this piece

  41. JU

    Jakob Uszkoreit quoted

    Our readingSelf-attention can yield more interpretable models.

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    ↗Attention is all you needarxiv.org 20th of 24 in this piece

  43. LJ

    Llion Jones quoted

    Our readingSelf-attention can yield more interpretable models.

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    ↗Attention is all you needarxiv.org 21st of 24 in this piece

  45. AG

    Aidan N. Gomez quoted

    Our readingSelf-attention can yield more interpretable models.

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    ↗Attention is all you needarxiv.org 22nd of 24 in this piece

  47. ŁK

    Łukasz Kaiser quoted

    Our readingSelf-attention can yield more interpretable models.

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    ↗Attention is all you needarxiv.org 23rd of 24 in this piece

  49. IP

    Illia Polosukhin quoted

    Our readingSelf-attention can yield more interpretable models.

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    ↗Attention is all you needarxiv.org 24th of 24 in this piece