

Pioneering AI Models for Regional Languages // Aleksa Gordić // #203
Jan 12, 2024
Aleksa Gordić, ex-Google DeepMind/Microsoft ML engineer, discusses pioneering AI models for regional languages, focusing on the development of YugoGPT. They explore unique language dynamics in the Balkans, business opportunities for multilingual models, and challenges in deploying large language models. The conversation delves into Aleksa's experience with vision and image models, collaborations with tech players, and use of advanced technologies. They also discuss open sourcing models, the lack of language support, and advantages/limitations of working for a company.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7 8
Introduction
00:00 • 2min
Synchronicities, Language Models, and GPUs
02:09 • 8min
Trying Open-Source Vector Databases and Taking Advantage of Support and Sponsorship
09:42 • 2min
Insights from Hosting Expert Speakers on Discord
11:59 • 20min
Challenges and Limitations of Language Models for Regional Languages
31:30 • 5min
Open Sourcing Models and Yugo GPT Development
36:04 • 5min
Open sourcing a checkpoint in the multi-lingual space
41:02 • 21min
Advantages and Limitations of Working for a Company
01:02:12 • 2min