BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Adapting and fine-tuning LLMs – a hands-on approach for business
  and science
DTSTART:20260611T070000Z
DTEND:20260611T130000Z
DTSTAMP:20260612T013900Z
UID:indico-event-3819@indico.ijs.si
CONTACT:events@slaif.si
DESCRIPTION:Speakers: Matej Klemen (University of Ljubljana\, Faculty of C
 omputer and Information Science)\, Živa Štebljaj\, Domen Vreš\, Marko R
 obnik-Šikonja\n\nCourse provider: University of Ljubljana\, Faculty of Co
 mputer and Information Science (UL FRI)Instructors: Matej Klemen (UL FRI)\
 , Domen Vreš (UL FRI)\, Živa Štebljaj (UL FRI)\, Marko Robnik-Šikonja 
 (UL FRI)\nLearning objectives: Get practical knowledge on how to use large
  language models (LLMs) via API calls\, their fine-tuning for specific tas
 ks\, and efficient inference.\nCourse contents: To use large language mode
 ls (LLMs) in a research or business setting\, it is necessary to i) to acc
 ess them on local computers or on GPU servers via API\, ii) adapt them to 
 specific needs by fine-tuning them.  The hands-on workshop will present t
 heoretically and practically\, step-by-step:\n\nHow LLMs can be used via A
 PI on a local or remote server.\nHow to fine-tune encoder-only models such
  as BERT.\nHow to fine-tune generative models such as Llama\, Gemma\, and 
 GaMS using compute-efficient techniques such as LoRA.\nHow to implement ef
 ficient LLM inference.\n\nThe work will be based on practical datasets and
  problems from business and research environments. The use cases will cove
 r a handful of selected tasks such as sentiment prediction\, information r
 etrieval\, and question answering.\nLearning outcomes: Practical knowledge
  of LLM API use and fine-tuning. Practical problem-solving skills with LLM
 s.\n\nhttps://indico.ijs.si/event/3819/
IMAGE;VALUE=URI:https://indico.ijs.si/event/3819/logo-1596601024.png
LOCATION:P02 (UL FRI)
URL:https://indico.ijs.si/event/3819/
END:VEVENT
END:VCALENDAR