CoEdIT
Collection
Collection of the publicly available CoEdIT dataset and instruction-tuned models for text editing.
•
6 items
•
Updated
•
6
This model was obtained by fine-tuning the corresponding google/flan-t5-xl
model on the CoEdIT-Composite dataset. Details of the dataset can be found in our paper and repository.
Paper: CoEdIT: Text Editing by Task-Specific Instruction Tuning
Authors: Vipul Raheja, Dhruv Kumar, Ryan Koo, Dongyeop Kang
We make available the models presented in our paper.
Model | Number of parameters |
---|---|
CoEdIT-large | 770M |
CoEdIT-xl | 3B |
CoEdIT-xxl | 11B |
Given an edit instruction and an original text, our model can generate the edited version of the text.
This model can also perform edits on composite instructions, as shown below:
from transformers import AutoTokenizer, T5ForConditionalGeneration
tokenizer = AutoTokenizer.from_pretrained("grammarly/coedit-xl-composite")
model = T5ForConditionalGeneration.from_pretrained("grammarly/coedit-xl-composite")
input_text = 'Fix grammatical errors in this sentence and make it simpler: 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)
https://github.com/vipulraheja/coedit
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