This paper presents Fauno, the first and largest open-source Italian conversational Large Language Model (LLM). Our goal with Fauno is to democratize the study of LLMs in Italian, demonstrating that obtaining a fine-tuned conversational bot with a single GPU is possible. In addition, we release a collection of datasets for conversational AI in Italian. The datasets on which we fine-tuned Fauno include various topics such as general question answering, computer science, and medical questions. We release our code and datasets on https://github.com/RSTLess-research/Fauno-Italian-LLM

Fauno: The Italian Large Language Model that will leave you senza parole! / Bacciu, Andrea; Trappolini, Giovanni; Santilli, Andrea; Rodolà, Emanuele; Silvestri, Fabrizio. - (2023). (Intervento presentato al convegno Italian Information Retrieval (IIR) 2023 tenutosi a Pisa).

Fauno: The Italian Large Language Model that will leave you senza parole!

Andrea Bacciu
Primo
;
Giovanni Trappolini
Secondo
;
Emanuele Rodolà
Penultimo
;
Fabrizio Silvestri
Ultimo
2023

Abstract

This paper presents Fauno, the first and largest open-source Italian conversational Large Language Model (LLM). Our goal with Fauno is to democratize the study of LLMs in Italian, demonstrating that obtaining a fine-tuned conversational bot with a single GPU is possible. In addition, we release a collection of datasets for conversational AI in Italian. The datasets on which we fine-tuned Fauno include various topics such as general question answering, computer science, and medical questions. We release our code and datasets on https://github.com/RSTLess-research/Fauno-Italian-LLM
2023
Italian Information Retrieval (IIR) 2023
large language model, large, language, model, llm
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Fauno: The Italian Large Language Model that will leave you senza parole! / Bacciu, Andrea; Trappolini, Giovanni; Santilli, Andrea; Rodolà, Emanuele; Silvestri, Fabrizio. - (2023). (Intervento presentato al convegno Italian Information Retrieval (IIR) 2023 tenutosi a Pisa).
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1698182
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact