We introduce StableLM 2 1.6B, the first in a new generation of our language model series. In this technical report, we present in detail the data and training procedure leading to the base and instruction-tuned versions of StableLM 2 1.6B. The weights for both models are available via Hugging Face for anyone to download and use. The report contains thorough evaluations of these models, including zero- and few-shot benchmarks, multilingual benchmarks, and the MT benchmark focusing on multi-turn dialogues. At the time of publishing this report, StableLM 2 1.6B was the state-of-the-art open model under 2B parameters by a significant margin. Given its appealing small size, we also provide throughput measurements on a number of edge devices. In addition, we open source several quantized checkpoints and provide their performance metrics compared to the original model.
@article{arxiv.2402.17834,
title = {Stable LM 2 1.6B Technical Report},
author = {Marco Bellagente and Jonathan Tow and Dakota Mahan and Duy Phung and Maksym Zhuravinskyi and Reshinth Adithyan and James Baicoianu and Ben Brooks and Nathan Cooper and Ashish Datta and Meng Lee and Emad Mostaque and Michael Pieler and Nikhil Pinnaparju and Paulo Rocha and Harry Saini and Hannah Teufel and Niccolo Zanichelli and Carlos Riquelme},
journal= {arXiv preprint arXiv:2402.17834},
year = {2024}
}