Skip to content

UK-07/LaMDA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LaMDA-pytorch

Open-source pre-training implementation of Google's LaMDA research paper in PyTorch.

Basic Usage - Pre-training

lamda_base = LaMDA(
    num_tokens = 20000,
    dim = 512,
    dim_head = 64,
    depth = 12,
    heads = 8
)

lamda = AutoregressiveWrapper(lamda_base, max_seq_len = 512)

tokens = torch.randint(0, 20000, (1, 512)) # mock token data

logits = lamda(tokens)

print(logits)

Citations

@article{DBLP:journals/corr/abs-2201-08239,
  author    = {Romal Thoppilan and
               Daniel De Freitas and
               Jamie Hall and
               Noam Shazeer and
               Apoorv Kulshreshtha and
               Heng{-}Tze Cheng and
               Alicia Jin and
               Taylor Bos and
               Leslie Baker and
               Yu Du and
               YaGuang Li and
               Hongrae Lee and
               Huaixiu Steven Zheng and
               Amin Ghafouri and
               Marcelo Menegali and
               Yanping Huang and
               Maxim Krikun and
               Dmitry Lepikhin and
               James Qin and
               Dehao Chen and
               Yuanzhong Xu and
               Zhifeng Chen and
               Adam Roberts and
               Maarten Bosma and
               Yanqi Zhou and
               Chung{-}Ching Chang and
               Igor Krivokon and
               Will Rusch and
               Marc Pickett and
               Kathleen S. Meier{-}Hellstern and
               Meredith Ringel Morris and
               Tulsee Doshi and
               Renelito Delos Santos and
               Toju Duke and
               Johnny Soraker and
               Ben Zevenbergen and
               Vinodkumar Prabhakaran and
               Mark Diaz and
               Ben Hutchinson and
               Kristen Olson and
               Alejandra Molina and
               Erin Hoffman{-}John and
               Josh Lee and
               Lora Aroyo and
               Ravi Rajakumar and
               Alena Butryna and
               Matthew Lamm and
               Viktoriya Kuzmina and
               Joe Fenton and
               Aaron Cohen and
               Rachel Bernstein and
               Ray Kurzweil and
               Blaise Aguera{-}Arcas and
               Claire Cui and
               Marian Croak and
               Ed H. Chi and
               Quoc Le},
  title     = {LaMDA: Language Models for Dialog Applications},
  journal   = {CoRR},
  volume    = {abs/2201.08239},
  year      = {2022},
  url       = {https://arxiv.org/abs/2201.08239},
  eprinttype = {arXiv},
  eprint    = {2201.08239},
  timestamp = {Fri, 22 Apr 2022 16:06:31 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2201-08239.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}
@misc{https://doi.org/10.48550/arxiv.1706.03762,
  doi = {10.48550/ARXIV.1706.03762},
  
  url = {https://arxiv.org/abs/1706.03762},
  
  author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, Lukasz and Polosukhin, Illia},
  
  keywords = {Computation and Language (cs.CL), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Attention Is All You Need},
  
  publisher = {arXiv},
  
  year = {2017},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}
@article{DBLP:journals/corr/abs-1808-06226,
  author    = {Taku Kudo and
               John Richardson},
  title     = {SentencePiece: {A} simple and language independent subword tokenizer
               and detokenizer for Neural Text Processing},
  journal   = {CoRR},
  volume    = {abs/1808.06226},
  year      = {2018},
  url       = {http://arxiv.org/abs/1808.06226},
  eprinttype = {arXiv},
  eprint    = {1808.06226},
  timestamp = {Sun, 02 Sep 2018 15:01:56 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1808-06226.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

About

Implementation of LaMDA model.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages