This model bases on T5-base model, finetuned using bbc-news-summary dataset
Example of using:
    
    def t5_summary(text: str):
        inputs = tokenizer.encode(
            "summarize: " + text,
            return_tensors='pt',
            max_length=2000,
            truncation=True,
            padding='max_length'
        ).to(torch.device("cuda"))
 
        # Generate the summary
        summary_ids = model.generate(
            inputs,
            max_length=250,
            num_beams=5
        )
        return tokenizer.decode(summary_ids[0], skip_special_tokens=True)