-
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque
Paper • 2506.07597 • Published -
HiTZ/Latxa-Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 826 • • 10 -
HiTZ/Latxa-Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 1.14k • 4 -
HiTZ/Latxa-Llama-3.1-70B-Instruct-FP8
Text Generation • 71B • Updated • 75 • 1
AI & ML interests
Natural Language Processing, Signal Processing
Recent Activity
Papers
MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification
Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages
HiTZ is a reference center on Language Technologies whose aim is to promote research, training, technological transfer and innovation in Artificial Intelligence focused on language and speech. It is a multidisciplinary team composed of people with backgrounds in computer science, linguistics and engineering, coming from the Ixa and Aholab research groups, both from the University of the Basque Country (UPV/EHU). These groups are -since their creation in 1988 and 1995 respectively- the main driving forces in the area of Language Technologies in the Basque Country.
-
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque
Paper • 2506.07597 • Published -
HiTZ/Latxa-Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 826 • • 10 -
HiTZ/Latxa-Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 1.14k • 4 -
HiTZ/Latxa-Llama-3.1-70B-Instruct-FP8
Text Generation • 71B • Updated • 75 • 1