Schneider-Kamp Lab

AI & ML interests

- Ressource constrained language modelling - Evaluation - Low-Bandwidth Distributed Training - Quantization - Medical Language Modelling - AI x Human

Recent Activity

JacobBITLABS  authored a paper about 5 hours ago

FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models

JacobBITLABS  submitted a paper about 5 hours ago

FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models

JacobBITLABS  updated a dataset about 6 hours ago

schneiderkamplab/SDU-Daisy

View all activity

Papers

FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models

When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization

View all Papers

Team members 6