OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909205734096896 |
|---|---|
| author | Masala, Mihai Ilie-Ablachim, Denis C. Corlatescu, Dragos Zavelca, Miruna Leordeanu, Marius Velicu, Horia Popescu, Marius Dascalu, Mihai Rebedea, Traian |
| author_facet | Masala, Mihai Ilie-Ablachim, Denis C. Corlatescu, Dragos Zavelca, Miruna Leordeanu, Marius Velicu, Horia Popescu, Marius Dascalu, Mihai Rebedea, Traian |
| contents | In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the training data is in English. Hence, their performance in English greatly exceeds their performance in other languages. This document presents our approach to training and evaluating the first foundational and chat LLM specialized for Romanian. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07703 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs Masala, Mihai Ilie-Ablachim, Denis C. Corlatescu, Dragos Zavelca, Miruna Leordeanu, Marius Velicu, Horia Popescu, Marius Dascalu, Mihai Rebedea, Traian Computation and Language In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the training data is in English. Hence, their performance in English greatly exceeds their performance in other languages. This document presents our approach to training and evaluating the first foundational and chat LLM specialized for Romanian. |
| title | OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.07703 |