Cite
Notes
Only stored in your browser.
Attribution
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
arXiv 2024
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
arXiv 2023
Landmark Attention: Random-Access Infinite Context Length for Transformers
from 3 papers
Martin Jaggi
Alejandro Hernández Cano
Alexandre Sallinen
Alireza Sakhaeirad
Andreas Köpf
Angelika Romanou
Antoine Bonnet
Antoine Bosselut
Axel Marmet
Bo Li