context compression

Artificial Intelligence Computation and Language

LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression

root September 26, 2023 0

This paper explores the potential to compress Large Language Models (LLMs) using Low Rank Decomposition (LoRD). The researchers found that ranks for linear layers in these models can be reduced…

Artificial Intelligence Computation and Language

In-context Autoencoder for Context Compression in a Large Language Model

root July 15, 2023 0

The team from Microsoft introduces In-context Autoencoder (ICAE), a novel method aimed at tackling the long context issue in large language models (LLMs). This approach seeks to compress lengthy contexts…

Page 1 of 1

Press ESC to close

context compression

Please allow ads on our site