google/t5-xxl-ssm-tqao

The model was fine-tuned on 90% of the train splits of Trivia QA (TQA) for 20k steps . It was pre-trained using T5's denoising objective on C4 . The model can be used as follows as follows for closed book question answering: t5_qa_model = AutoModelForSeq2SeqLM, AutoTokenizer.from_pretrained("google/t5-xxl-ssm-tqao") T5-11b: When was Franklin D. Roosevelt born? When was Roosevelt's birth? How much knowledge can be packed into the parameters of a language model? When asked?,