问如何使用BERT/ GPT-2进行释义生成？

EN

import torch
from transformers import T5ForConditionalGeneration, T5Tokenizer
# use here a backbone model of your choice, e.g. google/mt5-base
backbone_model = 'cointegrated/rut5-base-multitask' 
model = T5ForConditionalGeneration.from_pretrained(backbone_model)
tokenizer = T5Tokenizer.from_pretrained(backbone_model)
model.cuda();
optimizer = torch.optim.Adam(params=[p for p in model.parameters() if p.requires_grad], lr=1e-5)

# todo: load the paraphrasing corpus and define the get_batch function

for i in range(100500):
    xx, yy = get_batch(mult=mult)
    x = tokenizer(xx, return_tensors='pt', padding=True).to(model.device)
    y = tokenizer(yy, return_tensors='pt', padding=True).to(model.device)
    # do not force the model to predict pad tokens
    y.input_ids[y.input_ids==0] = -100
    loss = model(
        input_ids=x.input_ids,
        attention_mask=x.attention_mask,
        labels=y.input_ids,
        decoder_attention_mask=y.attention_mask,
        return_dict=True
    ).loss
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()

model.save_pretrained('my_paraphraser')
tokenizer.save_pretrained('my_paraphraser')

from transformers import pipeline
pipe = pipeline(task='text2text-generation', model='my_paraphraser')
print(pipe('Here is your text'))
# [{'generated_text': 'Here is the paraphrase or your text.'}]

print(pipe(
    'Here is your text', 
    encoder_no_repeat_ngram_size=3,  # make output different from input
    do_sample=True,  # randomize
    num_beams=5,  # try more options
    max_length=128,  # longer texts
))