8000 GitHub - gblackout/LM-OS: The compressor-retriever architecture for language model OS
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

gblackout/LM-OS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The Compressor-Retriever Architecture for Language Model OS

Yuan Yang, Siheng Xiong, Ehsan Shareghi and Faramarz Fekri

[Paper]

🚧 This repo is under heavy development

Overview

LLMs nowadays can process multimodal data, long documents, use tools, and browse web. Can we integrate all these and make a language model OS? Where the LLM acts as a CPU that processes data stored in a context window (RAM).

LM-OS

We argue the the key challenge towards LM OS is managing the life-long context and ensuring statefulness across sessions. To address this, we introduce compressor-retriever, a model-agnostic architecture designed for life-long context management. Our approach exclusively uses the base model's forward function to compress and retrieve context, ensuring end-to-end differentiability. Preliminary experiments demonstrate the effectiveness of this architecture in in-context learning tasks, marking a step towards the development of a fully stateful LLM OS.

Compressor-Retriever

About

The compressor-retriever architecture for language model OS

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  
0