BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2024//speaker//JUMZBA
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20230425T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231029T030000
RDATE:20241027T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T030000
RDATE:20250330T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Is GenAI All You Need to Classify Text? Some Learnings from the Tr
 enches - Marc Palyart\, Kateryna Budzyak
DTSTART;TZID=Europe/Berlin:20240424T131000
DTEND;TZID=Europe/Berlin:20240424T134000
DTSTAMP:20260811T175714Z
UID:pretalx-pyconde-pydata-2024-CWUQF3@pretalx.com
DESCRIPTION:In recent times\, GenAI has sparked fervent excitement\, somet
 imes touted as the panacea for all natural language processing (NLP) tasks
 . This presentation explores a practical text classification scenario at M
 alt\, highlighting the practical hurdles encountered when employing GenAI 
 (latency\, environmental impact\, and budgetary constraints). To overcome 
 these obstacles\, a smaller\, dedicated model emerged as a viable solution
 . We'll delve into the construction and optimization (quantization\, graph
  optimization) of this multilingual model. Finally we’ll see how GenAI's
  unparalleled zero-shot capabilities enables its continuous adaptation.
LOCATION:A1
URL:https://pretalx.com/pyconde-pydata-2024/talk/CWUQF3/
END:VEVENT
END:VCALENDAR