Bonn-Aachen International Center for Information Technology (b-it)
Neueste Zugänge
-
Towards Uncertainty-Aware Low-Bit Quantized LLMs for On-Device Inference
(2026-03-06)Quantizing large language models (LLMs) significantly reduces memory usage and computational requirements, enabling efficient on-device inference. However, aggressive quantization can degrade model performance and exacerbate ... -
Small and Fast LLMs on Commodity Hardware: Post-Training Quantization in llama.cpp
(2025-11-24)Large Language Models (LLMs) have demonstrated remarkable capabilities but their significant computational and memory demands hinder widespread deployment, especially on resource-constrained devices. Quantization, the ... -
SciREX: Scientific Relation Extraction: Natural Language Processing Lab : final report
(2025-09-23)The rapid growth of biomedical literature makes it increasingly difficult to identify and organize meaningful knowledge. This project addresses the problem by focusing on <strong>relation extraction (RE)</strong>, i.e., ...
RSS 1.0