T5 Paraphrase Paws

🚀 Paraphrase-Generation

A T5-based model for generating paraphrases of English sentences, trained on the Google PAWS dataset.

🚀 Quick Start

This is a T5 model designed for generating paraphrases of English sentences. It has been trained on the Google PAWS dataset.

✨ Features

• Generate paraphrases of English sentences.
• Available in both PyTorch and TF models.

📦 Installation

Requires sentencepiece: # !pip install sentencepiece

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Vamsi/T5_Paraphrase_Paws")  
model = AutoModelForSeq2SeqLM.from_pretrained("Vamsi/T5_Paraphrase_Paws").to('cuda')

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)

Advanced Usage

For more reference on training your own T5 model or using this model, do check out Paraphrase Generation.