Using roberta-base model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering.
32 Pulls Updated 7 months ago
e6836092461f · 42B
[INST] {{ .System }} {{ .Prompt }} [/INST]