philschmid

/

bart-large-cnn-samsum

like 268

Hi! I want to ask a question:

Model return summary in third preson only.
Example: My name is Nikita
Returns: Nikita's name is Nikita...
Could I change it?

Script for summary:

tokenizer = AutoTokenizer.from_pretrained("philschmid/bart-large-cnn-samsum")
model = AutoModelForSeq2SeqLM.from_pretrained("philschmid/bart-large-cnn-samsum")

def get_summary(tokenizer, model, text):
    tokens = tokenizer(text, truncation=True,
                       padding="longest", return_tensors="pt")
    summary = model.generate(**tokens)
    summary = tokenizer.decode(summary[0])
    return summary

get_summary(tokenizer=tokenizer, model=model, text="My name is Nikita" )

Thanks!