google/t5-11b-ssm-tqa

The model was pre-trained using T5's denoising objective on C4 . Pre-trained with REALM's salient span masking objective on Wikipedia . Fine-tuned on 100% of the train splits of Trivia QA (TQA) for 10 steps . The model can be used as follows for closed book question answering: t5_qa_model = AutoModelForSeq2SeqLM, AutoTokenizer.from_pretrained("google/t5-11b-ssm-tqa") T5-xxl: T5_tok (T5 QA) TQA: QA. QA QA,