H2O-Danube3 Technical Report

We present H2O-Danube3, a series of small language models consisting of H2O-Danube3-4B, trained on 6T tokens and H2O-Danube3-500M, trained on 4T tokens. Our models are pre-trained on high quality Web data consisting of primarily English tokens in three stages with different data mixes before final s...

Full description

Saved in:
Bibliographic Details
Main Authors Pfeiffer, Pascal, Singer, Philipp, Babakhin, Yauhen, Fodor, Gabor, Dhankhar, Nischay, Ambati, Sri Satish
Format Journal Article
LanguageEnglish
Published 12.07.2024
Subjects
Online AccessGet full text

Cover

Loading…