Scheduler, optimizer and trainer states are saved into this repo, so you can use that to continue finetune with your own data with existing gradients.

Usage

Summarization pipeline

python

from transformers import pipeline


pipe = pipeline('summarization', model='d0rj/rut5-base-summ')
pipe(text)

Text-to-text generation

python

from transformers import T5Tokenizer, T5ForConditionalGeneration


tokenizer = T5Tokenizer.from_pretrained('d0rj/rut5-base-summ')
model = T5ForConditionalGeneration.from_pretrained('d0rj/rut5-base-summ').eval()

input_ids = tokenizer(text, return_tensors='pt').input_ids
outputs = model.generate(input_ids)
summary = tokenizer.decode(outputs[0], skip_special_tokens=True)