T
ToolShelf
ENGRAM
// Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Engram

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

13EmergingUnknown
License
Apache-2.0
Updated
Today

What it does

This repository contains the official implementation for the paper: Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models. > Abstract: While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup. To address this, we explore conditional memory as a complementary sparsity axis, instantiated

Getting Started

git
git clone https://github.com/deepseek-ai/Engram

Platforms

🪟windows🍎mac🐧linux

Install Difficulty

moderate

Built With

python

Community Reactions