% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Penke:910080,
      author       = {Penke, Carolin and John, Chelsea Maria and Herten, Andreas
                      and Ebert, Jan and Kesselheim, Stefan and Suarez, Estela},
      title        = {{O}pen{GPT}-{X} - {T}raining {L}arge {L}anguage {M}odels on
                      {HPC} {S}ystems},
      reportid     = {FZJ-2022-03599},
      year         = {2022},
      abstract     = {Artificial neural networks represent an HPC workload with
                      increasing importance. In particular the field of Natural
                      Language Processing (NLP) has been undergoing a revolution
                      in recent years. The training of ever larger language
                      models, such as GPT-3, demands large HPC resources and has
                      the potential to greatly impact everyday technology. The
                      OpenGPT-X project was established in 2022 and aims to not
                      leave this field to large tech companies but to provide an
                      open, publicly funded alternative based on European values.
                      The Jülich Supercomputing Centre is a consortium partner
                      providing HPC infrastructure for the pre-training of the
                      models. We research the optimization potential in the
                      training process for example by using novel accelerator
                      architectures.},
      month         = {Sep},
      date          = {2022-09-28},
      organization  = {14th JLESC Workshop, Urbana-Champaign
                       (USA), 28 Sep 2022 - 30 Sep 2022},
      subtyp        = {After Call},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / ATML-X-DEV - ATML
                      Accelerating Devices (ATML-X-DEV)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(DE-Juel-1)ATML-X-DEV},
      typ          = {PUB:(DE-HGF)24},
      url          = {https://juser.fz-juelich.de/record/910080},
}