ILSP & Archimedes NLP Theme Talk

LSP & Archimedes NLP Theme Talk, Thursday 7 March, 16:00 (Greek time)
Speaker: Preslav Nakov
Title: "Jais and Jais-chat: Building the World's Best Open Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models"
Room: Zampolli, Athena Main Building (6 Artemidos str., Marousi, ground floor)
and virtually via MS Teams:
https://teams.microsoft.com/l/meetup-join/19%3ameeting_NDgzMjM1MTQtYWFiMS00ZDk4LTlhYmItOTg1NDlhYWRjNTg3%40thread.v2/0?context=%7b%22Tid%22%3a%226ae07702-c5f7-4f38-9b87-acad62a75d93%22%2c%22Oid%22%3a%22735f6987-4242-47ec-98d6-f1eb55fb371f%22%7d

* Meeting ID: 364 885 596 720
* Passcode: jbYNHY

Abstract:
I will discuss Jais and Jais-chat, two state-of-the-art Arabic-centric foundation and instruction-tuned open generative large language models (LLMs). The models are based on the GPT-3 decoder-only architecture and are pretrained on a mixture of Arabic and English texts, including source code in various programming languages. The models demonstrate better knowledge and reasoning capabilities in Arabic than previous open Arabic and multilingual models by a sizable margin, based on extensive evaluation. Moreover, they are competitive in English compared to English-centric open models of similar size, despite being trained on much less English data. I will discuss the training, the tuning, the safety alignment, and the evaluation, as well as the lessons we learned.

Stay tuned for future events:
For ways to receive news about the Archimedes Unit and its meetings, check https://archimedesai.gr/en/. To subscribe to the mailing list of Archimedes, send a message with title "subscribe archimedes-news Firstname LastName" (where Firstname and LastName are your First and Last Name respectively) to sympa@lists.athenarc.gr<mailto:sympa@lists.athenarc.gr>. The body of the message may be blank
If you are an AI researcher or practitioner, please consider becoming a member of the Hellenic Artificial Intelligence Society (EETN, http://www.eetn.gr/en/).