% 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:1034059,
      author       = {Penke, Carolin},
      title        = {{A}n {I}ntroduction to {L}arge {L}anguage {M}odels},
      reportid     = {FZJ-2024-06880},
      year         = {2024},
      abstract     = {Large Language Models (LLMs) have revolutionized the field
                      of artificial intelligence, enabling advanced text
                      generation and understanding. This talk provides a concise
                      overview of LLMs, focusing on their development,
                      architecture, and implementation. We explain key concepts,
                      and give details on the backbone of modern LLMs: the
                      transformer architecture and its innovative attention
                      mechanism. To be able to train these models on
                      supercomputers, advanced parallelization techniques are
                      needed. Recent advancements and promising trends are
                      identified. Through the lens of the OpenGPT-X project, this
                      presentation will highlight the collaborative efforts in
                      developing multilingual, open-source LLMs.},
      month         = {Jun},
      date          = {2024-06-06},
      organization  = {Women in Data Science Conference
                       Chemnitz, Chemnitz (Germany), 6 Jun
                       2024 - 7 Jun 2024},
      subtyp        = {Plenary/Keynote},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / 5122 - Future Computing
                      $\&$ Big Data Systems (POF4-512) / OpenGPT-X - Aufbau eines
                      Gaia-X Knotens für große KI-Sprachmodelle und innovative
                      Sprachapplikations-Services; Teilvorhaben: Optimierung und
                      Skalierung auf großen HPC-Systemen (68GX21007F) / JuWinHPC
                      - Jülich Women in HPC (JuWinHPC)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(DE-HGF)POF4-5122 /
                      G:(DE-Juel-1)68GX21007F / G:(DE-Juel-1)JuWinHPC},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/1034059},
}