BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260623T113557Z
UID:15c8684a-8aa6-4031-a721-a5946819cb31
DTSTART:20250226T090000Z
DTEND:20250226T170000Z
DESCRIPTION:We will introduce Large Language Models (LLMs)\, focusing on th
 eir core architecture\, training methodologies\, practical applications\, 
 and some important considerations. We begin with a brief exploration of th
 e transformer architecture\, examining how architectural choices and scali
 ng laws have shaped modern language models. We then investigate key traini
 ng paradigms\, with particular emphasis on Reinforcement Learning from Hum
 an Feedback (RLHF) and instruction tuning\, while briefly touching on emer
 ging approaches like Direct Preference Optimisation (DPO). The discussion 
 progresses through the evolution of knowledge integration techniques\, fro
 m basic context stuffing to Retrieval-Augmented Generation (RAG)\, highlig
 hting their practical implications. We will discuss the critical issue of
  hallucinations in LLM outputs\, providing concrete examples and verificat
 ion strategies. To conclude\, a quick overview of the current software lan
 dscape and immediate future developments in the field\, and a look ahead t
 o the rest of the webinar series.
LOCATION:\, 
SUMMARY:Basics of Large Language Models - transformers to LLMs
URL;VALUE=URI:https://www.ebi.ac.uk/training/events/basics-large-language-m
 odels-transformers-llms
END:VEVENT
END:VCALENDAR