This repository provides datasets, models and code for CoEdIT the instruction-tuned text editing models, with the official implementation of the following paper:
CoEdIT: Text Editing by Task-Specific Instruction Tuning
Vipul Raheja, Dhruv Kumar, Ryan Koo, and Dongyeop Kang
Our code is based on Hugging Face transformers.
Coming soon.
Coming soon.
Coming soon.
We have uploaded all our model checkpoints to Hugging Face.
| Model | Params |
|---|---|
| CoEdIT-large | 770M |
| CoEdIT-xl | 3B |
| CoEdIT-xxl | 11B |
| CoEdIT-xl-composite | 3B |
You can directly load our models using Hugging Face Transformers.
from transformers import AutoTokenizer, T5ForConditionalGeneration
tokenizer = AutoTokenizer.from_pretrained("grammarly/coedit-xl")
model = T5ForConditionalGeneration.from_pretrained("grammarly/coedit-xl")
input_text = 'Fix grammatical errors in this sentence: New kinds of vehicles will be invented with new technology than today.'
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)[0]Coming soon.