metadata

license: cc-by-nc-4.0
datasets:
  - asset
  - wi_locness
  - GEM/wiki_auto_asset_turk
  - discofuse
  - zaemyung/IteraTeR_plus
  - jfleg
  - grammarly/coedit
language:
  - en
metrics:
  - sari
  - bleu
  - accuracy

Model Card for CoEdIT-xxl

This model was obtained by fine-tuning the corresponding google/flan-t5-xxl model on the CoEdIT dataset.

Paper: CoEdIT: ext Editing by Task-Specific Instruction Tuning

Authors: Vipul Raheja, Dhruv Kumar, Ryan Koo, Dongyeop Kang

Model Details

Model Description

Language(s) (NLP): English
Finetuned from model: google/flan-t5-xxl

Model Sources

Repository: https://github.com/vipulraheja/coedit
Paper: https://arxiv.org/abs/2305.09857

How to use

We make available the models presented in our paper.

Model	Number of parameters
CoEdIT-large	770M
CoEdIT-xl	3B
CoEdIT-xxl	11B

Uses

Text Revision Task

Given an edit instruction and an original text, our model can generate the edited version of the text.

Usage

from transformers import AutoTokenizer, T5ForConditionalGeneration

tokenizer = AutoTokenizer.from_pretrained("grammarly/coedit-xxl")
model = T5ForConditionalGeneration.from_pretrained("grammarly/coedit-xxl")
input_text = 'Fix grammatical errors in this sentence: When I grow up, I start to understand what he said is quite right.'
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
outputs = model.generate(input_ids, max_length=256)
edited_text = tokenizer.decode(outputs[0], skip_special_tokens=True)

Software

https://github.com/vipulraheja/coedit

Citation

BibTeX:

@article{raheja2023coedit,
      title={CoEdIT: Text Editing by Task-Specific Instruction Tuning}, 
      author={Vipul Raheja and Dhruv Kumar and Ryan Koo and Dongyeop Kang},
      year={2023},
      eprint={2305.09857},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

APA: Raheja, V., Kumar, D., Koo, R., & Kang, D. (2023). CoEdIT: Text Editing by Task-Specific Instruction Tuning. ArXiv. /abs/2305.09857