Skip to main content

Attention Free Transformer - Pytorch

Project description

aft-pytorch

Unofficial PyTorch implementation of Attention Free Transformer's layers by Zhai, et al. [abs, pdf] from Apple Inc.

Installation

You can install aft_pt via pip:

pip install aft_pt

Usage

You can import the AFT-Full or AFT-Simple layer (as described in the paper) from the package like so:

AFTFull

from aft_pt import AFTFull

layer = AFTFull(
    max_seqlen=20,
    dim=512,
    hidden_dim=64
)

# a batch of sequences with 10 timesteps of length 512 each
x = torch.rand(32, 10, 512)
y = layer(x) # [32, 10, 512]

AFTSimple

from aft_pt import AFTSimple

layer = AFTSimple(
    max_seqlen=20,
    dim=512,
    hidden_dim=64
)

# a batch of sequences with 10 timesteps of length 512 each
x = torch.rand(32, 10, 512)
y = layer(x) # [32, 10, 512]

AFTLocal

from aft_pt import AFTLocal

layer = AFTLocal(
    max_seqlen=20,
    dim=512,
    hidden_dim=64
)

# a batch of sequences with 10 timesteps of length 512 each
x = torch.rand(32, 10, 512)
y = layer(x) # [32, 10, 512]

This layer wrapper is a 'plug-and-play' with your existing networks / Transformers. You can swap out the Self-Attention layer with the available layers in this package with minimal changes.

TODO

  • Add full AFT architecture
  • Add variants like, AFTConv
  • Benchmark using Karpathy's minGPT

Contributing

If you like this repo, please leave a star! If there are any amends or suggestions, feel free to raise a PR/issue.

Credits

@misc{attention-free-transformer,
title = {An Attention Free Transformer},
author = {Shuangfei Zhai and Walter Talbott and Nitish Srivastava and Chen Huang and Hanlin Goh and Ruixiang Zhang and Josh Susskind},
year = {2021},
URL = {https://arxiv.org/pdf/2105.14103.pdf}
}

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

aft_pt-0.1.0.tar.gz (4.6 kB view hashes)

Uploaded source

Built Distribution

aft_pt-0.1.0-py3-none-any.whl (4.9 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page