001038632 001__ 1038632
001038632 005__ 20250203215421.0
001038632 037__ $$aFZJ-2025-01603
001038632 041__ $$aEnglish
001038632 1001_ $$0P:(DE-Juel1)140202$$aStrube, Alexandre$$b0$$eCorresponding author
001038632 1112_ $$a2. IT-Forum 2024$$cJülich$$wGermany
001038632 245__ $$aHelmholtz Blablador - An experimental Large Language Model server$$f2024-05-23 - 
001038632 260__ $$c2024
001038632 3367_ $$033$$2EndNote$$aConference Paper
001038632 3367_ $$2DataCite$$aOther
001038632 3367_ $$2BibTeX$$aINPROCEEDINGS
001038632 3367_ $$2ORCID$$aLECTURE_SPEECH
001038632 3367_ $$0PUB:(DE-HGF)31$$2PUB:(DE-HGF)$$aTalk (non-conference)$$btalk$$mtalk$$s1738562167_21856$$xOther
001038632 3367_ $$2DINI$$aOther
001038632 500__ $$aTalk in an internal format of Forschungszentrum Jülich.
001038632 520__ $$aAlexandre Strube (JSC) stellt in seinem Vortrag das Large Language System Blablador vor, das im Rahmen der HIFIS-Kooperation angeboten wird. Der Vortrag wird in englischer Sprache gehalten.AbstractRecent 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
001038632 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001038632 536__ $$0G:(DE-Juel-1)E54.303.11$$aHelmholtz AI Consultant Team FB Information (E54.303.11)$$cE54.303.11$$x1
001038632 909CO $$ooai:juser.fz-juelich.de:1038632$$pVDB
001038632 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)140202$$aForschungszentrum Jülich$$b0$$kFZJ
001038632 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001038632 9141_ $$y2024
001038632 920__ $$lyes
001038632 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001038632 980__ $$atalk
001038632 980__ $$aVDB
001038632 980__ $$aI:(DE-Juel1)JSC-20090406
001038632 980__ $$aUNRESTRICTED