app.py

import gradio as gr
import torch

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("ramsrigouthamg/t5-large-paraphraser-diverse-high-quality")
tokenizer = AutoTokenizer.from_pretrained("ramsrigouthamg/t5-large-paraphraser-diverse-high-quality")

device = torch.device("cude" if torch.cuda.is_available() else "cpu")
model = model.to(device)

def generate_text(inp):
  text = "paraphrase: "+context + " </s>"
  context = inp
  encoding = tokenizer.encode_plus(text, max_length=256, padding=True, return_tensors="pt")
  input_ids, attention_mask = encoding["input_ids"].to(device), encoding["attention_mask"].to(device)
  model.eval()
  diverse_beams_output = model.generate(
    input_ids=input_ids, attention_mask= attention_mask, max_length=256, early_stopping=True, num_beams=5, num_beam_groups=5, num_return_sequences=5, diversity_penalty=0.70)
    
  sent = tokenizer.decode(diverse_beams_outputs[0], skip_special_tokens = True, clean_up_tokenization_spaces = True)
  return sent
  
output_text = gr.outputs.Textbox()
gr.Interface(generate_text, "textbox", output_text).launch(inline=False)