Oct. 30, 2023, 4:30 p.m. | Venelin Valkov

Venelin Valkov www.youtube.com

Imagine you had an unlimited context window for #LLMs? MemGPT helps you overcome the token count limit by using a hierarchical memory, similar to Operating Systems. MemGPT uses the concepts of fast memory - current context window (like RAM) and slow memory - external storage (like HDD). RAM is super fast, but it's limited in size compared to HDD.

Full text tutorial: https://www.mlexpert.io/prompt-engineering/memgpt

Paper: https://arxiv.org/abs/2310.08560
MemGPT GitHub: https://github.com/cpacker/MemGPT/
MemGPT Web Page: https://memgpt.ai/

Discord: https://discord.gg/UaNPxVD6tv
Prepare for the Machine Learning interview: …

concepts context context window count current demo hierarchical installation llms memory operating systems paper review storage systems token

More from www.youtube.com / Venelin Valkov

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

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Business Data Scientist, gTech Ads

@ Google | Mexico City, CDMX, Mexico

Lead, Data Analytics Operations

@ Zocdoc | Pune, Maharashtra, India