all AI news
Efficient Streaming Language Models with Attention Sinks (Paper Explained)
Oct. 14, 2023, 9:43 p.m. | Yannic Kilcher
Yannic Kilcher www.youtube.com
How does one run inference for a generative autoregressive language model that has been trained with a fixed context size? Streaming LLMs combine the performance of windowed attention, but avoid the drop in performance by using attention sinks - an interesting phenomenon where the token at position 0 acts as an absorber of "extra" attention.
OUTLINE:
0:00 - Introduction
1:20 - What is the problem?
10:30 - The hypothesis: Attention Sinks
15:10 - Experimental evidence
18:45 - …
attention chatgpt context explained generative inference language language model language models llm llms paper performance streaming token
More from www.youtube.com / Yannic Kilcher
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne