RigoChat 2: an adapted language model to Spanish using a bounded dataset and reduced hardware
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916649554149376 |
|---|---|
| author | Gómez, Gonzalo Santamaría Subies, Guillem García Ruiz, Pablo Gutiérrez Valero, Mario González Fuertes, Natàlia Zamorano, Helena Montoro Sanz, Carmen Muñoz Plaza, Leire Rosado García, Nuria Aldama Sánchez, David Betancur Sushkova, Kateryna Nieto, Marta Guerrero Jiménez, Álvaro Barbero |
| author_facet | Gómez, Gonzalo Santamaría Subies, Guillem García Ruiz, Pablo Gutiérrez Valero, Mario González Fuertes, Natàlia Zamorano, Helena Montoro Sanz, Carmen Muñoz Plaza, Leire Rosado García, Nuria Aldama Sánchez, David Betancur Sushkova, Kateryna Nieto, Marta Guerrero Jiménez, Álvaro Barbero |
| contents | Large Language Models (LLMs) have become a key element of modern artificial intelligence, demonstrating the ability to address a wide range of language processing tasks at unprecedented levels of accuracy without the need of collecting problem-specific data. However, these versatile models face a significant challenge: both their training and inference processes require substantial computational resources, time, and memory. Consequently, optimizing this kind of models to minimize these requirements is crucial. In this article, we demonstrate that, with minimal resources and in a remarkably short time, it is possible to enhance a state-of-the-art model, specifically for a given language task, without compromising its overall capabilities using a relatively small pretrained LLM as a basis. Specifically, we present our use case, RigoChat 2, illustrating how LLMs can be adapted to achieve superior results in Spanish-language tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08188 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RigoChat 2: an adapted language model to Spanish using a bounded dataset and reduced hardware Gómez, Gonzalo Santamaría Subies, Guillem García Ruiz, Pablo Gutiérrez Valero, Mario González Fuertes, Natàlia Zamorano, Helena Montoro Sanz, Carmen Muñoz Plaza, Leire Rosado García, Nuria Aldama Sánchez, David Betancur Sushkova, Kateryna Nieto, Marta Guerrero Jiménez, Álvaro Barbero Computation and Language Artificial Intelligence Large Language Models (LLMs) have become a key element of modern artificial intelligence, demonstrating the ability to address a wide range of language processing tasks at unprecedented levels of accuracy without the need of collecting problem-specific data. However, these versatile models face a significant challenge: both their training and inference processes require substantial computational resources, time, and memory. Consequently, optimizing this kind of models to minimize these requirements is crucial. In this article, we demonstrate that, with minimal resources and in a remarkably short time, it is possible to enhance a state-of-the-art model, specifically for a given language task, without compromising its overall capabilities using a relatively small pretrained LLM as a basis. Specifically, we present our use case, RigoChat 2, illustrating how LLMs can be adapted to achieve superior results in Spanish-language tasks. |
| title | RigoChat 2: an adapted language model to Spanish using a bounded dataset and reduced hardware |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.08188 |