app.py

import gradio as gr
from transformers import BartForConditionalGeneration, BartTokenizer

model = BartForConditionalGeneration.from_pretrained("hyechanjun/interview-question-remake")
tok = BartTokenizer.from_pretrained("hyechanjun/interview-question-remake")

def genQuestion(context):
    inputs = tok.tokenize(context, return_tensors="pt")
    output = model.generate(inputs["input_ids"], num_beams=4, max_length=64)

    return tok.batch_decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=False)

iface = gr.Interface(fn=genQuestion, inputs="text", outputs="text")
iface.launch()