H2O-Danube-1.8B Technical Report

Philipp Singer, Pascal Pfeiffer, Yauhen Babakhin, Maximilian Jeblick, Nischay Dhankhar, Gabor Fodor, sri ambati

H2O-Danube-1.8B Technical Report: 18 upvotes on Hugging Face Daily Papers, #6 of 14 papers on 2024-01-31. Day-by-day upvote history.

We present H2O-Danube-1.8B, a 1.8B language model trained on 1T tokens following the core principles of LLama 2 and Mistral. We leverage and refine various techniques for pre-training large language models. Although our model is trained on significantly fewer total tokens compared to reference models of similar size, it exhibits highly competitive metrics across a multitude of benchmarks. We additionally release a chat model trained with supervised fine-tuning followed by direct preference optimization. We make H2O-Danube-1.8B openly available under Apache 2.0 license further democratizing LLMs to a wider audience economically.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.