% 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{Strube:1038638,
      author       = {Strube, Alexandre},
      title        = {{H}elmholtz {B}lablador: {A}n {I}nference {S}erver for
                      {S}cientific {L}arge {L}anguage {M}odels},
      reportid     = {FZJ-2025-01609},
      year         = {2024},
      abstract     = {Recent advances in large language models (LLMs) like
                      chatGPT have demonstrated their potential for generating
                      human-like text and reasoning about topics with natural
                      language. However, applying these advanced LLMs requires
                      significant compute resources and expertise that are out of
                      reach for most academic researchers. To make scientific LLMs
                      more accessible, we have developed Helmholtz Blablador, an
                      open-source inference server optimized for serving
                      predictions from customized scientific LLMs.Blablador
                      provides the serving infrastructure to make models
                      accessible via a simple API without managing servers,
                      firewalls, authentication or infrastructure. Researchers can
                      add their pretrained LLMs to the central hub. Other
                      scientists can then query the collective model catalog via
                      web or using the popular OpenAI api to add LLM functionality
                      in other tools, like programming IDEs.This enables a
                      collaborative ecosystem for scientific LLMs:Researchers
                      train models using datasets and GPUs from their own lab. No
                      need to set up production servers. They can even provide
                      their models with inference happening on cpus, with the use
                      of tools like llama.cpp.Models are contributed to the
                      Blablador hub through a web UI or API call. Blablador
                      handles loading models and publishing models for general
                      use.Added models become available for querying by other
                      researchers.A model catalog displays available LLMs from
                      different labs and research areas.Besides that, one can
                      train, quantize, fine-tune and evaluate LLMs directly with
                      Blablador.The inference server is available at
                      http://helmholtz-blablador.fz-juelich.de},
      month         = {Jun},
      date          = {2025-06-12},
      organization  = {Helmholtz AI Conference, Düsseldorf
                       (Germany), 12 Jun 2025 - 14 Jun 2025},
      subtyp        = {Other},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / Helmholtz AI Consultant
                      Team FB Information (E54.303.11)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(DE-Juel-1)E54.303.11},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/1038638},
}