Mae'r model LLM yn seiliedig ar microsoft/phi-2, gyda hyfforddiant parhaus ar 100k llinell o ddata Cymreig o'r dataset allenai/MADLAD-400 am 1 Epoch.

Pwrpas y model yw fod yn gychwyn i hyfforddiant cywrain pellach i greu casgliad o LLMs Cymreig penodol.


Contains information from allenai/MADLAD-400 which is made available under the ODC Attribution License.

Downloads last month
111
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Dataset used to train BangorAI/phi2-cy-100k