BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.scipy.org//2024//speaker//FBWCH9
BEGIN:VTIMEZONE
TZID:US/Pacific
BEGIN:DAYLIGHT
DTSTART:20230710T000000
TZNAME:PDT
TZOFFSETFROM:-0700
TZOFFSETTO:-0700
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T020000
RDATE:20241103T020000
TZNAME:PST
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240310T030000
RDATE:20250309T030000
TZNAME:PDT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Generative AI Copilot for Scientific Software – a RAG-Based Appr
 oach using OLMo - Don Setiawan\, Anshul Tambay\, Cordero Core\, Niki Burgg
 raf\, Anant Mittal\, Ishika Khandelwal\, Anuj Sinha\, Madhav Kashyap\, Van
 i Mandava
DTSTART;TZID=US/Pacific:20240709T133000
DTEND;TZID=US/Pacific:20240709T173000
DTSTAMP:20261014T160443Z
UID:pretalx-2024-BZGQMC@cfp.scipy.org
DESCRIPTION:Generative AI systems built upon large language models (LLMs) 
 have shown great promise as tools that enable people to access information
  through natural conversation. Scientists can benefit from the breakthroug
 hs these systems enable to create advanced tools that will help accelerate
  their research outcomes. This tutorial will cover: (1) the basics of lang
 uage models\, (2) setting up the environment for using open source LLMs wi
 thout the use of expensive compute resources needed for training or fine-t
 uning\, (3) learning a technique like Retrieval-Augmented Generation (RAG)
  to optimize output of LLM\, and (4) build a “production-ready” app to
  demonstrate how researchers could turn disparate knowledge bases into spe
 cial purpose AI-powered tools. The right audience for our tutorial is scie
 ntists and research engineers who want to use LLMs for their work.
LOCATION:Ballroom D
URL:https://cfp.scipy.org/2024/talk/BZGQMC/
END:VEVENT
END:VCALENDAR