EuroLLM: Multilingual Language Models for Europe
Research paper by Pedro Henrique Martins and collaborators. Published 2024-09-24. Topics: open-weight LLMs, EuroLLM project, multilingual LLMs, scaling laws, multilingual tokenizer.
Resource information
- Authors
- Pedro Henrique Martins, Patrick Fernandes, João Alves, Nuno M. Guerreiro, Ricardo Rei, Duarte M. Alves, José Pombal, Amin Farajian, Manuel Faysse, Mateusz Klimaszewski, Pierre Colombo, Barry Haddow, José G. C. de Souza, Alexandra Birch, André F. T. Martins
- Research topics
- open-weight LLMs, EuroLLM project, multilingual LLMs, scaling laws, multilingual tokenizer, data mix, modeling configurations, EuroLLM-1.7B, EuroLLM-1.7B-Instruct
- Publication date
- 2024-09-24
- Publication
- arXiv
- Last record update
- Nov 3, 2026
