Aimv2 3B Patch14 336

🚀 AIMv2 Vision Model

The AIMv2 family of vision models is pre - trained with a multimodal autoregressive objective, offering high - performance solutions for various vision tasks.

🚀 Quick Start

This README provides an introduction to the AIMv2 family of vision models, including their performance metrics, usage examples, and citation information.

✨ Features

• High - performance on benchmarks: Outperforms OAI CLIP, SigLIP on most multimodal understanding benchmarks and DINOv2 on open - vocabulary object detection and referring expression comprehension.
• Strong recognition ability: The AIMv2 - 3B model achieves 89.5% accuracy on ImageNet using a frozen trunk.
• Multimodal pre - training: Trained with a multimodal autoregressive objective, which is simple and easy to scale.

📦 Model Information

Model Performance

The aimv2 - 3B - patch14 - 336 model has the following performance on different classification tasks:

💻 Usage Examples

Basic Usage - PyTorch

import requests
from PIL import Image
from transformers import AutoImageProcessor, AutoModel

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

processor = AutoImageProcessor.from_pretrained(
    "apple/aimv2-3B-patch14-336",
)
model = AutoModel.from_pretrained(
    "apple/aimv2-3B-patch14-336",
    trust_remote_code=True,
)

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)

Basic Usage - JAX

import requests
from PIL import Image
from transformers import AutoImageProcessor, FlaxAutoModel

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

processor = AutoImageProcessor.from_pretrained(
    "apple/aimv2-3B-patch14-336",
)
model = FlaxAutoModel.from_pretrained(
    "apple/aimv2-3B-patch14-336",
    trust_remote_code=True,
)

inputs = processor(images=image, return_tensors="jax")
outputs = model(**inputs)

📄 License

This project is licensed under the apple - amlr license.

📚 Documentation

For more information about the AIMv2 models, please refer to the [AIMv2 Paper].

📖 Citation

If you find our work useful, please consider citing us as:

@misc{fini2024multimodalautoregressivepretraininglarge,
  author      = {Fini, Enrico and Shukor, Mustafa and Li, Xiujun and Dufter, Philipp and Klein, Michal and Haldimann, David and Aitharaju, Sai and da Costa, Victor Guilherme Turrisi and Béthune, Louis and Gan, Zhe and Toshev, Alexander T and Eichner, Marcin and Nabi, Moin and Yang, Yinfei and Susskind, Joshua M. and El-Nouby, Alaaeldin},
  url         = {https://arxiv.org/abs/2411.14402},
  eprint      = {2411.14402},
  eprintclass = {cs.CV},
  eprinttype  = {arXiv},
  title       = {Multimodal Autoregressive Pre-training of Large Vision Encoders},
  year        = {2024},
}