Spivavtor
Collection
Dataset and models from the paper "Spivavtor: An Instruction Tuned Ukrainian Text Editing Model" (accepted at the Third Ukrainian NLP Workshop).
•
3 items
•
Updated
This model was obtained by instruction tuning bigscience/mt0-large
model on the Spivavtor dataset. All details of the dataset and 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
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 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("grammarly/spivavtor-large")
model = AutoModelForSeq2SeqLM.from_pretrained("grammarly/spivavtor-large")
# 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)