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

Using sentencepiece vocabulary was shrinking from 250K to 20K (top 20K English tokens) the number of model parameters reduced to 244M parameters, and model size reduced from 2.2GB to 0.9GB - 39% of the original one.

Approach was taken from article: How to adapt a multilingual T5 model for a single language.

Downloads last month: 16

Inference API

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.