Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian
Research paper by Michael Hoffmann and collaborators. Published 2025-09-06. Topics: trilingual foundation model, Llama 3.1-8B, Llama-GENBA-10B, multilingual corpus, unified tokenizer.
Resource information
- Authors
- Michael Hoffmann, Jophin John, Stefan Schweter, Gokul Ramakrishnan, Hoi-Fong Mak, Alice Zhang, Dmitry Gaynullin, Nicolay J. Hammer
- Research area
- Language technology
- Application domain
- General AI research
- AI methods
- Large language models
- Research topics
- cs.CL, cs.AI
- arXiv record date
- 2025-09-06
- Publication date
- 2025-09-06
- Publication
- arXiv
- Upstream last modified
- Sep 9, 2025
- Last record update
- Nov 3, 2026
Abstract
We present Llama-GENBA-10B, a trilingual foundation model addressing English-centric bias in large language models. Built on Llama 3.1-8B and scaled to 10B parameters, Llama-GENBA-10B is continuously pretrained on 164B tokens (82B English, 82B German, and 80M Bavarian), balancing resources while preventing English dominance. Targeted at the German NLP community, the model also promotes Bavarian as a low-resource language. Development tackled four challenges: (1) curating a multilingual corpus despite Bavarian scarcity, (2) creating a unified tokenizer for English, German, and Bavarian, (3) optimizing architecture and language-ratio hyperparameters for cross-lingual transfer, and (4) establishing the first standardized trilingual evaluation suite by translating German benchmarks into Bavarian. Evaluations show that Llama-GENBA-10B achieves strong cross-lingual performance, with the fine-tuned variant surpassing Apertus-8B-2509 and gemma-2-9b in Bavarian and establishing itself as the best model in its class for this language, while also outperforming EuroLLM in English and matching its results in German. Training on the Cerebras CS-2 demonstrated efficient large-scale multilingual pretraining with documented energy use, offering a blueprint for inclusive foundation models that integrate low-resource languages.