georgedavila / bart-large-mnli-classifier

Zero-shot classifier which classifies text into categories of your choosing. Returns a dictionary of the most likely class and all class likelihoods.

  • Public
  • 406 runs
  • GitHub

Run time and cost

This model costs approximately $0.0014 to run on Replicate, or 714 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 7 seconds.

Readme

Output is a dictionary with key ‘mostLikelyClass’ giving the most likely class and key ‘allClasses’ giving a dictionary of all class likelihoods.