mlenjoyneer/rut5_large_sum_gazeta

RuT5LargeSumGazeta

Model description

This is the model for abstractive summarization for Russian based on ai-forever/ruT5-large.

Intended uses & limitations

How to use

Here is how to use this model in PyTorch:

from transformers import AutoTokenizer, T5ForConditionalGeneration

model_name = "mlenjoyneer/rut5_large_sum_gazeta"
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,
    no_repeat_ngram_size=4
)[0]

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

Training data

• Dataset: Gazeta

Evaluation results

Model	R-1-f	R-2-f	R-L-f	chrF	BLEU	Avg char length
IlyaGusev/mbart_ru_sum_gazeta	28.7	11.1	24.4	37.3	9.4	373
IlyaGusev/rut5_base_sum_gazeta	28.6	11.1	24.5	37.2	9.4	331
IlyaGusev/rugpt3medium_sum_gazeta	24.1	6.5	19.8	32.1	3.6	242
rut5-large_sum_gazeta	29.6	11.7	25.2	37.3	9.4	304