Model Description

Fine-tuning of uk-mt5-base model on summarization dataset.

How to Use

from transformers import AutoTokenizer, T5ForConditionalGeneration, pipeline

tokenizer = AutoTokenizer.from_pretrained('ukr-models/uk-summarizer')
model = T5ForConditionalGeneration.from_pretrained('ukr-models/uk-summarizer')

ppln = pipeline("summarization", model=model, tokenizer=tokenizer, device=0, max_length=128, num_beams=4, no_repeat_ngram_size=2, clean_up_tokenization_spaces=True)

text = "..."
ppln(text)