from transformers import (
    AutoModelForSeq2SeqLM,
    AutoTokenizer
)

model_checkpoint = "consciousAI/question-generation-auto-t5-v1-base-s-q"

model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

## Input with prompt
context="question_context: <context>"
encodings = tokenizer.encode(context, return_tensors='pt', truncation=True, padding='max_length').to(device)

## You can play with many hyperparams to condition the output, look at demo
output = model.generate(encodings, 
                        #max_length=300, 
                        #min_length=20, 
                        #length_penalty=2.0, 
                        num_beams=4,
                        #early_stopping=True,
                        #do_sample=True,
                        #temperature=1.1
                       )

## Multiple questions are expected to be delimited by '?' You can write a small wrapper to elegantly format. Look at the demo.
questions = [tokenizer.decode(id, clean_up_tokenization_spaces=False, skip_special_tokens=False) for id in output]