| language: en | |
| A simple question-generation model built based on SQuAD 2.0 dataset. | |
| Example use: | |
| ```python | |
| from transformers import T5Config, T5ForConditionalGeneration, T5Tokenizer | |
| model_name = "allenai/t5-small-squad2-question-generation" | |
| tokenizer = T5Tokenizer.from_pretrained(model_name) | |
| model = T5ForConditionalGeneration.from_pretrained(model_name) | |
| def run_model(input_string, **generator_args): | |
| input_ids = tokenizer.encode(input_string, return_tensors="pt") | |
| res = model.generate(input_ids, **generator_args) | |
| output = tokenizer.batch_decode(res, skip_special_tokens=True) | |
| print(output) | |
| return output | |
| run_model("shrouds herself in white and walks penitentially disguised as brotherly love through factories and parliaments; offers help, but desires power;") | |
| run_model("He thanked all fellow bloggers and organizations that showed support.") | |
| run_model("Races are held between April and December at the Veliefendi Hippodrome near Bakerky, 15 km (9 miles) west of Istanbul.") | |
| ``` | |
| which should result in the following: | |
| ``` | |
| ['What is the name of the man who is a brotherly love?'] | |
| ['What did He thank all fellow bloggers and organizations that showed support?'] | |
| ['Where is the Veliefendi Hippodrome located?'] | |
| ``` | |