Paraphrase-Generation
β
Model description
β T5 Model for generating paraphrases of english sentences. Trained on the Google PAWS dataset. β
How to use
β## Requires sentencepiece: # !pip install sentencepiece PyTorch and TF models available β
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
β
tokenizer = AutoTokenizer.from_pretrained("Vamsi/T5_Paraphrase_Paws")
model = AutoModelForSeq2SeqLM.from_pretrained("Vamsi/T5_Paraphrase_Paws").to('cuda')
β
sentence = "This is something which i cannot understand at all"
text = "paraphrase: " + sentence + " </s>"
encoding = tokenizer.encode_plus(text,pad_to_max_length=True, return_tensors="pt")
input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda")
outputs = model.generate(
input_ids=input_ids, attention_mask=attention_masks,
max_length=256,
do_sample=True,
top_k=120,
top_p=0.95,
early_stopping=True,
num_return_sequences=5
)
for output in outputs:
line = tokenizer.decode(output, skip_special_tokens=True,clean_up_tokenization_spaces=True)
print(line)
β
For more reference on training your own T5 model or using this model, do check out Paraphrase Generation.
- Downloads last month
- 43,405