from transformers import AutoTokenizer, T5ForConditionalGeneration

model_name = "IlyaGusev/rut5_base_headline_gen_telegram"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = T5ForConditionalGeneration.from_pretrained(model_name)

article_text = "..."

input_ids = tokenizer(
    [article_text],
    max_length=600,
    add_special_tokens=True,
    padding="max_length",
    truncation=True,
    return_tensors="pt"
)["input_ids"]

output_ids = model.generate(
    input_ids=input_ids
)[0]

headline = tokenizer.decode(output_ids, skip_special_tokens=True)
print(headline)

Training data

Dataset: ru_all_split.tar.gz

Training procedure

Training script: train.py