They are in sp (Sentence Piece) format. Need to convert them into huggingface format.
The terms:
"kn" = Kannada
"ml" = Malayalam
"ta" = Tamil
"te" = Telugu
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.