BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//program.berlinbuzzwords.de//bbuzz25//speaker//RP87NY
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20240617T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:How to train a fast LLM for coding tasks - Ivan Dolgov
DTSTART;TZID=Europe/Berlin:20250617T160000
DTEND;TZID=Europe/Berlin:20250617T164000
DTSTAMP:20261015T114304Z
UID:pretalx-bbuzz25-WFWTFL@program.berlinbuzzwords.de
DESCRIPTION:Coding LLMs are now part of our daily work\, making coding eas
 ier. In this talk\, we share how we built an in-house LLM for AI code comp
 letion in JetBrains products\, covering design choices\, data preparation
 \, training\, and model’s evaluation.
LOCATION:Frannz Salon
URL:https://program.berlinbuzzwords.de/bbuzz25/talk/WFWTFL/
END:VEVENT
END:VCALENDAR