Total runs:
12.0M
Run Growth:
5.4M
Growth Rate:
45.36%
Sponsored by
ZenMux
apple / aimv2-large-patch14-224
Model's Last Updated: July 09 2025
image-feature-extraction
Introduction of aimv2-large-patch14-224
Model Details of aimv2-large-patch14-224
Introduction
[
AIMv2 Paper
] [
BibTeX
]
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 scale effectively. Some AIMv2 highlights include:
- Outperforms OAI CLIP and SigLIP on the majority of multimodal understanding benchmarks.
- Outperforms DINOv2 on open-vocabulary object detection and referring expression comprehension.
- Exhibits strong recognition performance with AIMv2-3B achieving 89.5% on ImageNet using a frozen trunk .
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-large-patch14-224",
)
model = AutoModel.from_pretrained(
"apple/aimv2-large-patch14-224",
trust_remote_code=True,
)
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
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-large-patch14-224",
)
model = FlaxAutoModel.from_pretrained(
"apple/aimv2-large-patch14-224",
trust_remote_code=True,
)
inputs = processor(images=image, return_tensors="jax")
outputs = model(**inputs)
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},
}
Runs of apple aimv2-large-patch14-224 on huggingface.co
1.3K
Total runs
1
24-hour runs
-47
3-day runs
-393
7-day runs
-248
30-day runs
More Information About aimv2-large-patch14-224 huggingface.co Model
Url of aimv2-large-patch14-224
aimv2-large-patch14-224 huggingface.co Url
Provider of aimv2-large-patch14-224 huggingface.co
Other API from apple
Updated:March 01 2025
Total runs:
2.5M
Run Growth:
-269.3K
Growth Rate:
-10.89%
Total runs:
1.5M
Run Growth:
-9.1K
Growth Rate:
-0.59%
Total runs:
1.2M
Run Growth:
-1.1M
Growth Rate:
-87.65%
Total runs:
104.0K
Run Growth:
59.2K
Growth Rate:
56.90%
Total runs:
95.4K
Run Growth:
-6.3K
Growth Rate:
-6.59%
Total runs:
10.5K
Run Growth:
4.7K
Growth Rate:
44.96%
Total runs:
7.6K
Run Growth:
-6.8K
Growth Rate:
-90.08%
Total runs:
6.9K
Run Growth:
4.4K
Growth Rate:
63.25%
Total runs:
4.7K
Run Growth:
1.8K
Growth Rate:
39.35%
Total runs:
4.6K
Run Growth:
2.5K
Growth Rate:
52.75%
Total runs:
4.1K
Run Growth:
2.0K
Growth Rate:
48.02%
Total runs:
4.0K
Run Growth:
954
Growth Rate:
23.93%
Total runs:
3.9K
Run Growth:
288
Growth Rate:
7.41%
Total runs:
3.7K
Run Growth:
-54
Growth Rate:
-1.45%
Total runs:
2.3K
Run Growth:
2.0K
Growth Rate:
85.50%
Total runs:
1.8K
Run Growth:
328
Growth Rate:
18.67%
Total runs:
1.6K
Run Growth:
743
Growth Rate:
47.26%
Total runs:
1.0K
Run Growth:
291
Growth Rate:
28.28%
Total runs:
1.0K
Run Growth:
-37
Growth Rate:
-3.63%
Total runs:
838
Run Growth:
-740
Growth Rate:
-89.59%
Total runs:
813
Run Growth:
-760
Growth Rate:
-93.48%
Total runs:
715
Run Growth:
-468
Growth Rate:
-47.46%
Total runs:
590
Run Growth:
298
Growth Rate:
50.51%
Total runs:
515
Run Growth:
311
Growth Rate:
63.08%
Total runs:
478
Run Growth:
326
Growth Rate:
61.51%
Total runs:
452
Run Growth:
31
Growth Rate:
6.86%
Total runs:
415
Run Growth:
133
Growth Rate:
32.68%
Total runs:
380
Run Growth:
-199
Growth Rate:
-52.37%
Total runs:
370
Run Growth:
130
Growth Rate:
35.91%
Total runs:
290
Run Growth:
-632
Growth Rate:
-196.27%
Total runs:
266
Run Growth:
-58
Growth Rate:
-21.80%
Total runs:
265
Run Growth:
166
Growth Rate:
62.64%
Total runs:
256
Run Growth:
131
Growth Rate:
51.17%
Total runs:
234
Run Growth:
90
Growth Rate:
38.46%
Total runs:
223
Run Growth:
-81
Growth Rate:
-36.32%
Total runs:
212
Run Growth:
84
Growth Rate:
39.62%
Total runs:
211
Run Growth:
134
Growth Rate:
63.51%
Total runs:
201
Run Growth:
145
Growth Rate:
72.14%
Total runs:
177
Run Growth:
153
Growth Rate:
86.44%
Total runs:
170
Run Growth:
-67
Growth Rate:
-39.41%
Total runs:
169
Run Growth:
122
Growth Rate:
72.19%
Total runs:
166
Run Growth:
50
Growth Rate:
30.12%
Total runs:
154
Run Growth:
131
Growth Rate:
85.06%
Total runs:
146
Run Growth:
136
Growth Rate:
93.15%
Total runs:
138
Run Growth:
66
Growth Rate:
47.83%
Total runs:
131
Run Growth:
-43
Growth Rate:
-32.82%
Total runs:
125
Run Growth:
80
Growth Rate:
64.00%
Total runs:
120
Run Growth:
107
Growth Rate:
89.17%
Total runs:
111
Run Growth:
71
Growth Rate:
63.96%
Total runs:
108
Run Growth:
67
Growth Rate:
62.04%
Total runs:
108
Run Growth:
-63
Growth Rate:
-58.33%
Total runs:
99
Run Growth:
-61
Growth Rate:
-61.62%
Total runs:
69
Run Growth:
18
Growth Rate:
26.09%
Total runs:
58
Run Growth:
-23
Growth Rate:
-39.66%
Total runs:
57
Run Growth:
54
Growth Rate:
94.74%
Total runs:
53
Run Growth:
-45
Growth Rate:
-84.91%
Total runs:
46
Run Growth:
-95
Growth Rate:
-206.52%