Spivavtor-xxl: An Open-Source Ukrainian Text Editing Model - Free Text Rewriting, Simplification, and Grammar Correction

Spivavtor Xxl

Developed by grammarly

Spivavtor-xxl is an instruction fine-tuned Ukrainian text editing model based on the CohereForAI/aya-101 model, focusing on tasks such as text rewriting, simplification, and grammar correction.

Large Language Model

Transformers

Other#Ukrainian text editing #Instruction fine-tuning #Grammar correction

Downloads 43

Release Time : 3/29/2024

Model Overview

Through instruction fine-tuning on Ukrainian text, this model can perform various text editing tasks including rewriting, simplification, grammar correction, and coherence improvement.

Model Features

Multi-task text editing

Capable of performing various text editing tasks, including rewriting, simplification, grammar correction, and coherence improvement

Ukrainian language optimization

Specially optimized for Ukrainian text, providing high-quality editing results

Instruction fine-tuning

Enables the model to understand and execute specific text editing instructions through instruction fine-tuning

Model Capabilities

Text rewriting

Sentence simplification

Grammar correction

Text coherence improvement

Use Cases

Content creation

Text rewriting

Helps users express the same content in different ways

Generates semantically identical but differently phrased text

Text optimization

Grammar correction

Automatically detects and corrects grammatical errors in text

Outputs grammatically correct text

Sentence simplification

Simplifies complex sentences into more understandable forms

Generates clearer and more concise sentences

🚀 Model Card for Spivavtor-xxl

This model addresses the need for Ukrainian text editing by leveraging instruction tuning. It is based on the CohereForAI/aya-101 model, offering enhanced performance on the Spivavtor dataset for various text - editing tasks.

🚀 Quick Start

This model was obtained by instruction tuning the CohereForAI/aya-101 model on the Spivavtor dataset. All details of the dataset and the fine - tuning process can be found in our paper.

Paper: Spivavtor: An Instruction Tuned Ukrainian Text Editing Model

Authors: Aman Saini, Artem Chernodub, Vipul Raheja, Vivek Kulkarni

✨ Features

The widget section showcases the model's capabilities in different text - editing scenarios:

Paraphrasing example: "Перефразуйте речення: Який найкращий комплiмент, який ти отримував вiд будь - кого?"
Simplification example: "Спростiть речення: Там він помер через шість тижнів, 13 січня 888 року."
GEC example: "Виправте граматику в цьому реченнi: Дякую за інформацію! ми з Надією саме вийшли з дому"
Coherence example: "Виправте зв’язнiсть в реченнi: Лінч досі відмовляється розповідати про сумнозвісну травневу дорожньо - транспортну пригоду, коли він збив жінку - пішохода в районі нічного клубу Баффало та відлетів. Той факт, що Лінч взагалі говорив, заслуговує на увагу в цих краях."

📚 Documentation

Model Details

Model Description

Property	Details
Language	Ukrainian
Finetuned from model	CohereForAI/aya-101

How to use

We make the following models available from our paper.

Model	Number of parameters	Reference name in Paper
Spivavtor-large	1.2B	SPIVAVTOR-MT0-LARGE
Spivavtor-xxl	13B	SPIVAVTOR-AYA-101

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("grammarly/spivavtor-xxl")
model = AutoModelForSeq2SeqLM.from_pretrained("grammarly/spivavtor-xxl")

# Paraphrase the sentence: What is the greatest compliment that you ever received from anyone?
input_text = 'Перефразуйте речення: Який найкращий комплімент, який ти отримував від будь-кого?'

inputs = tokenizer.encode(input_text, return_tensors="pt")
output = model.generate(inputs, max_length=256)
output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)

📄 License

The model is licensed under cc-by-4.0.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご