Datasets created for SFT of GaMS models
AI & ML interests
language description, standardisation, language technologies, terminology, multilingualism, adapting to people with disabilities
Recent Activity
View all activity
GaMS based machine translator specialised for translating to Slovene
Slovene GaMS models based on Google's Gemma 3
Gemma 2 based models continually-pretrained and instruction tuned for Slovene
Datasets created for SFT of GaMS models
Datasets that were created (either by OCR or translation) for pretraining of GaMS models
GaMS based machine translator specialised for translating to Slovene
Gemma 2 based GaMS model with longer context
Slovene GaMS models based on Google's Gemma 3
Next generation of GaMS models. Includes GaMS-Instruct models additionally improved using subset of nvidia/Nemotron-Post-Training-Dataset-v1.
Gemma 2 based models continually-pretrained and instruction tuned for Slovene