GPT-SW3: An Autoregressive Language Model for the Nordic Languages

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ekgren, Ariel, Gyllensten, Amaru Cuba, Stollenwerk, Felix, Öhman, Joey, Isbister, Tim, Gogoulou, Evangelia, Carlsson, Fredrik, Heiman, Alice, Casademont, Judit, Sahlgren, Magnus
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910661620006912
author Ekgren, Ariel
Gyllensten, Amaru Cuba
Stollenwerk, Felix
Öhman, Joey
Isbister, Tim
Gogoulou, Evangelia
Carlsson, Fredrik
Heiman, Alice
Casademont, Judit
Sahlgren, Magnus
author_facet Ekgren, Ariel
Gyllensten, Amaru Cuba
Stollenwerk, Felix
Öhman, Joey
Isbister, Tim
Gogoulou, Evangelia
Carlsson, Fredrik
Heiman, Alice
Casademont, Judit
Sahlgren, Magnus
contents This paper details the process of developing the first native large generative language model for the Nordic languages, GPT-SW3. We cover all parts of the development process, from data collection and processing, training configuration and instruction finetuning, to evaluation and considerations for release strategies. We hope that this paper can serve as a guide and reference for other researchers that undertake the development of large generative models for smaller languages.
format Preprint
id arxiv_https___arxiv_org_abs_2305_12987
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GPT-SW3: An Autoregressive Language Model for the Nordic Languages
Ekgren, Ariel
Gyllensten, Amaru Cuba
Stollenwerk, Felix
Öhman, Joey
Isbister, Tim
Gogoulou, Evangelia
Carlsson, Fredrik
Heiman, Alice
Casademont, Judit
Sahlgren, Magnus
Computation and Language
Artificial Intelligence
This paper details the process of developing the first native large generative language model for the Nordic languages, GPT-SW3. We cover all parts of the development process, from data collection and processing, training configuration and instruction finetuning, to evaluation and considerations for release strategies. We hope that this paper can serve as a guide and reference for other researchers that undertake the development of large generative models for smaller languages.
title GPT-SW3: An Autoregressive Language Model for the Nordic Languages
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2305.12987