Salvato in:
Dettagli Bibliografici
Autori principali: Uhlig, Matthias, Schacht, Sigurd, Barkur, Sudarshan Kamath
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2401.10580
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917570579267584
author Uhlig, Matthias
Schacht, Sigurd
Barkur, Sudarshan Kamath
author_facet Uhlig, Matthias
Schacht, Sigurd
Barkur, Sudarshan Kamath
contents Large language models have gained immense importance in recent years and have demonstrated outstanding results in solving various tasks. However, despite these achievements, many questions remain unanswered in the context of large language models. Besides the optimal use of the models for inference and the alignment of the results to the desired specifications, the transfer of models to other languages is still an underdeveloped area of research. The recent publication of models such as Llama-2 and Zephyr has provided new insights into architectural improvements and the use of human feedback. However, insights into adapting these techniques to other languages remain scarce. In this paper, we build on latest improvements and apply the Direct Preference Optimization(DPO) approach to the German language. The model is available at https://huggingface.co/DRXD1000/Phoenix.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10580
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PHOENIX: Open-Source Language Adaption for Direct Preference Optimization
Uhlig, Matthias
Schacht, Sigurd
Barkur, Sudarshan Kamath
Computation and Language
Large language models have gained immense importance in recent years and have demonstrated outstanding results in solving various tasks. However, despite these achievements, many questions remain unanswered in the context of large language models. Besides the optimal use of the models for inference and the alignment of the results to the desired specifications, the transfer of models to other languages is still an underdeveloped area of research. The recent publication of models such as Llama-2 and Zephyr has provided new insights into architectural improvements and the use of human feedback. However, insights into adapting these techniques to other languages remain scarce. In this paper, we build on latest improvements and apply the Direct Preference Optimization(DPO) approach to the German language. The model is available at https://huggingface.co/DRXD1000/Phoenix.
title PHOENIX: Open-Source Language Adaption for Direct Preference Optimization
topic Computation and Language
url https://arxiv.org/abs/2401.10580