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
- 14
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.