A small T5v1.1 model trained on the cLang-8 dataset following the process described in A Simple Recipe for Multilingual Grammatical Error Correction.

Since it is a single-task T5v1.1 model, there is no need for a task-specific prefix.

Downloads last month
1
Safetensors
Model size
77M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for Buntan/gec-t5-v1_1-small