BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pycon-lithuania-2024//speaker//NCSV9C
BEGIN:VTIMEZONE
TZID:Europe/Vilnius
BEGIN:DAYLIGHT
DTSTART:20230406T000000
TZNAME:EEST
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231029T040000
RDATE:20241027T040000
TZNAME:EET
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T040000
RDATE:20250330T040000
TZNAME:EEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:🧼 From GPU-poor to data-rich: data quality practices for LLM fi
 ne-tuning - Gabriel Martín Blázquez\, David Berenstein
DTSTART;TZID=Europe/Vilnius:20240405T140000
DTEND;TZID=Europe/Vilnius:20240405T142500
DTSTAMP:20261011T090529Z
UID:pretalx-pycon-lithuania-2024-BGF8R3@pretalx.com
DESCRIPTION:If you are GPU-poor you need to become data-rich. I will give 
 an overview of what we learned from looking at Alpaca\, LIMA\, Dolly\, Ult
 raFeedback and Zephyr and how we applied that to fine-tuning a state-of-th
 e-art open source LLM called Notus and Notux by becoming data-rich.
LOCATION:Room 111
URL:https://pretalx.com/pycon-lithuania-2024/talk/BGF8R3/
END:VEVENT
END:VCALENDAR