Episode Notes → [ Ссылка ]
This week’s guests are Barret Zoph and Liam Fedus, research scientists at Google Brain. Our conversation centered around Large Language Models (LLM), specifically recent work by Barret, Liam, and their collaborators on efficient scaling of large language models.
***Sections*** ↓
Introduction to Liam Fedus and Barret Zoph and to Google Brain - 00:00:03
Scaling language models - 00:03:17
Efficiency metrics and magnitudes of improvement - 00:11:30
Are these language models multilingual? - 00:13:04
Models and specialized training for setup - 00:15:28
Language Models for data scientists and other practitioners - 00:17:49
API and multistage pipelines - 00:20:01
Computer vision - 00:20:58
What is doable and practical in multimodal models? - 00:22:17
What are one or two things you are most excited about? - 00:23:52
Pathways - 00:27:05

свернуть