BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Foundations of LLM Mastery: Fine-tuning on one GPU
DTSTART:20250908T070000Z
DTEND:20250908T103000Z
DTSTAMP:20260905T201000Z
UID:indico-event-203@events.asc.ac.at
CONTACT:training@asc.ac.at
DESCRIPTION:Start date:  08 Sept 2025\, 09:00 (CEST)     Entry level: 
  IntermediateEnd date:  08 Sept 2025\, 12:30 (CEST)   Subject area:  
 Artificial IntelligenceLocation:  ONLINE (Zoom)     Topics:  Large La
 nguage ModelsLanguage:  English     Target audience:  Industry\, publ
 ic sector\, academiaPrice:  Free (for eligible participants)     Organ
 izers:  ASC & EuroCC Austria & AI:ATFine-tuning large language models (LL
 Ms) often requires substantial resources\, yet recent advancements allow f
 or effective training on a single GPU.This practical\, 3.5-hour course int
 roduces industry professionals — from start-ups to SMEs and large enterp
 rises — to efficient techniques for fine-tuning LLMs without sacrificing
  model performance.In this course\, participants will learn about:Quantiza
 tion: Techniques to reduce model memory requirements\, enabling the deploy
 ment of LLMs on resource-constrained hardware.Parameter-Efficient Fine-Tun
 ing (PEFT) with LoRA: Fine-tune large models by adjusting a limited set of
  parameters\, reducing computational load while achieving high-quality res
 ults.Through hands-on exercises and guided demos\, participants will gain 
 practical experience in fine-tuning LLMs using these methods\, setting the
  stage for immediate application in real-world projects\, from question an
 swering chat bots in an online shop to digital layers interpreting the nat
 ional law in the context of a specific case. The possibilities are endless
 .By the end of this course\, participants will have developed a foundation
 al understanding of techniques reducing the memory footprint of a large la
 nguage model during fine-tuning and inference.Agenda & ContentFor a detail
 ed timetable and additional information\, please see Agenda & Content in t
 he left menu.Entry levelIntermediatePrerequisitesBasic programming skills 
 in Python.                Having worked with Pytorch would
  be beneficial.Target audienceCourse for academia\, industry\, and public 
 administration.Course formatThis course will be delivered as a LIVE ONLINE
  COURSE (using Zoom).Hands-on labsAll participants will get a temporary us
 er account on LEONARDO to do the hands-on labs.You will use your own lapto
 p or workstation to connect conveniently from your browser to a LEONARDO J
 upyterlab session and do the hands-on exercisesLecturersSimeon Harrison (I
 NiTS and EuroCC Austria)Martin Pfister (ACA – Advanced Computing Austria
  GmbH and EuroCC Austria)LanguageEnglishDate\, time\, and location08.09.20
 25\, 09:00 – 12:30 CEST\, LIVE ONLINE COURSE (using Zoom)Prices and elig
 ibilityThis course is partly funded by the EuroCC 2 project. Therefore\, t
 he course is open and free of charge for participants from academia\, indu
 stry\, and public administration from the Member States (MS) of the Europe
 an Union (EU) and Associated/Other Countries to the Horizon 2020 programme
 .RegistrationThe registration form and deadlines are available from the le
 ft menu. The registration form might close even before the deadline if the
  number of registrations has reached its maximum (and will open again if t
 here are cancelations).Please register with your official email address to
  prove your affiliation.You will get an automatic confirmation via email (
 subject starting with "[Indico] Registration")\, please check your Spam/Ju
 nk folders.Following your successful registration\, you will receive furth
 er information approximately 1 week before the course.WaitinglistAfter the
  number of registrations has reached its maximum or the registration form 
 has been closed\, you may want to send us an email stating that you are in
 terested to be put on the waiting list (vacancies may occur due to cancela
 tions\, etc.).To be able to do the hands-on labs on the ASC please provide
  your full international mobile-phone number for the two-factor authentica
 tion required to login to the ASC systems.Modification\, withdrawal & no-s
 how policyYour registration is binding. Please only register for the cours
 e if you are really going to attend.You can update your registration data 
 or withdraw your registration anytime before the registration form has bee
 n closed via the link "Manage my registration" which you can find at the b
 ottom of your automatic email confirmation (subject starting with "[Indico
 ] Registration").Alternatively\, or after the registration form has been c
 losed\, please inform us about your cancelation or any change in your regi
 stration data (especially your mobile-phone number) via email (training@as
 c.ac.at).No-show policy: If you do not cancel and do not show up at the co
 urse you will be blacklisted and excluded from future training events.Orga
 nizers                This course is jointly organized by the 
 ASC Research Center\, TU Wien\, EuroCC Austria\, and AI:AT.Acknowledgement
 sThis course is partially funded by the EuroCC 2 project.The project has r
 eceived funding from the European High-Performance Computing Joint Underta
 king (JU) under grant agreement No 101101903. The JU receives support from
  the Digital Europe Programme and Austria\, Belgium\, Bulgaria\, Croatia\,
  Cyprus\, Czech Republic\, Denmark\, Estonia\, Finland\, France\, Germany\
 , Greece\, Hungary\, Iceland\, Ireland\, Italy\, Latvia\, Lithuania\, Luxe
 mbourg\, Montenegro\, Netherlands\, North Macedonia\, Norway\, Poland\, Po
 rtugal\, Romania\, Serbia\, Slovakia\, Slovenia\, Spain\, Sweden\, and Tü
 rkiye.Additional funding for the project comes from the Austrian federal m
 inistries BMBWF and BMK.\n\nhttps://events.asc.ac.at/event/203/
URL:https://events.asc.ac.at/event/203/
END:VEVENT
END:VCALENDAR