cointegrated/rut5-base-paraphraser

🤗 Hugging Face sourcemit244M params977 MBsafetensors✓ 3 checksumsupdated today

Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo cointegrated/rut5-base-paraphraser ./model-folder

Needs a seeder →

This is a paraphraser for Russian sentences described in this Habr post.

It is recommended to use the model with the encoder_no_repeat_ngram_size argument:

from transformers import T5ForConditionalGeneration, T5Tokenizer
MODEL_NAME = 'cointegrated/rut5-base-paraphraser'
model = T5ForConditionalGeneration.from_pretrained(MODEL_NAME)
tokenizer = T5Tokenizer.from_pretrained(MODEL_NAME)
model.cuda();
model.eval();

def paraphrase(text, beams=5, grams=4, do_sample=False):
    x = tokenizer(text, return_tensors='pt', padding=True).to(model.device)
    max_size = int(x.input_ids.shape[1] * 1.5 + 10)
    out = model.generate(**x, encoder_no_repeat_ngram_size=grams, num_beams=beams, max_length=max_size, do_sample=do_sample)
    return tokenizer.decode(out[0], skip_special_tokens=True)

print(paraphrase('Каждый охотник желает знать, где сидит фазан.'))
# Все охотники хотят знать где фазан сидит.