Default Models List

Get a summary of the default models for all the tasks covered in the course.

We'll cover the following

As a reference, we've provided a summarized list of all the tasks covered in the course along with the default models.


For Natural Language Processing, the following are the default models for respective tasks.

  • Text classification: distilbert-base-uncased-finetuned-sst-2-english
  • Token classification: dslim/bert-base-NER
  • Text summarization: sshleifer/distilbart-cnn-12-6
  • Question answering: distilbert-base-cased-distilled-squad
  • Text generation: gpt2
  • Text similarity: sentence-transformers/all-mpnet-base-v2
  • Translation: t5-base
  • Fill mask: distilroberta-base

Computer vision

The default models for computer vision tasks are as follows:

  • Image classification: google/vit-base-patch16-224
  • Object detection: facebook/detr-resnet-50
  • Segmentation: facebook/detr-resnet-50-panoptic

Create a free account to view this lesson.

By signing up, you agree to Educative's Terms of Service and Privacy Policy