This is a smaller version of the google/mt5-base model with only Russian and some English embeddings left.

  • The original model has 582M parameters, with 384M of them being input and output embeddings.
  • After shrinking the sentencepiece vocabulary from 250K to 30K (top 10K English and top 20K Russian tokens) the number of model parameters reduced to 244M parameters, and model size reduced from 2.2GB to 0.9GB - 42% of the original one.

The creation of this model is described in the post How to adapt a multilingual T5 model for a single language along with the source code.

Downloads last month
157
Hosted inference API
Text2Text Generation
This model can be loaded on the Inference API on-demand.