This model is t5-small based and was trained using squad-v2 dataset to generate plausible answers (i.e. extract entities) from a context.
You must use special token <ha>to delimiter the sentence you want to extract answers and also, start the input text as "generate answers"
Below is an example of usage:
extract answers:
Several days before Colorado Congresswoman Lauren Boebert and a male companion were kicked out of a Denver showing of “Beetlejuice,” the representative of Colorado's 3rd congressional district spent campaign funds at his bar, filings with the Federal Election Commission show.
According to Boebert’s official filings with the Federal Election Commission dated Oct. 14, Boebert spent $317.48 at Hooch Craft Cocktail Bar in Aspen on July 31 for “Event Catering”, more than 10 days prior to the “Beetlejuice” incident.
<ha> The Aspen, Colo. based bar is owned by Quinn Gallagher, 46, who was later revealed to be Boebert’s escort on the night that both were booted from the theater. <ha>
The expected output will be answers with <sep> tokens. For instance, in the above example, Quinn Gallagher `
- Downloads last month
- 239