hugpadhugpad

apple / aimv2-large-patch14-224-lit

Vision437M7.6K9Updated Jul 8, 2025
Hugging Face

Downloads

7.6K

Likes

9

Last updated

Jul 8, 2025

License

apple-amlr

We introduce the AIMv2 family of vision models pre-trained with a multimodal autoregressive objective. AIMv2 pre-training is simple and straightforward to train and to scale effectively. Some AIMv2 highlights include:

Tasks & library

  • zero shot image classification
  • transformers

Tags

  • transformers
  • jax
  • aimv2
  • feature-extraction
  • vision
  • mlx

Technical specifications

Parameters437M
Librarytransformers
LanguagesNot available
Licenseapple-amlr