Total runs:
12.0M
Run Growth:
5.5M
Growth Rate:
45.55%
Sponsored by
APIMart
apple / aimv2-huge-patch14-448
Model's Last Updated: July 09 2025
image-feature-extraction
Introduction of aimv2-huge-patch14-448
Model Details of aimv2-huge-patch14-448
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-huge-patch14-448",
)
model = AutoModel.from_pretrained(
"apple/aimv2-huge-patch14-448",
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-huge-patch14-448",
)
model = FlaxAutoModel.from_pretrained(
"apple/aimv2-huge-patch14-448",
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-huge-patch14-448 on huggingface.co
274
Total runs
3
24-hour runs
8
3-day runs
28
7-day runs
171
30-day runs
More Information About aimv2-huge-patch14-448 huggingface.co Model
Url of aimv2-huge-patch14-448
aimv2-huge-patch14-448 huggingface.co Url
Provider of aimv2-huge-patch14-448 huggingface.co
Other API from apple
Updated:March 01 2025
Total runs:
2.6M
Run Growth:
-166.7K
Growth Rate:
-6.57%
Total runs:
1.6M
Run Growth:
10.7K
Growth Rate:
0.69%
Total runs:
1.3M
Run Growth:
-1.1M
Growth Rate:
-85.55%
Total runs:
110.1K
Run Growth:
34.7K
Growth Rate:
32.86%
Total runs:
102.4K
Run Growth:
9.5K
Growth Rate:
9.65%
Total runs:
10.7K
Run Growth:
4.6K
Growth Rate:
43.96%
Total runs:
6.6K
Run Growth:
3.3K
Growth Rate:
47.11%
Total runs:
4.8K
Run Growth:
1.9K
Growth Rate:
40.20%
Total runs:
4.6K
Run Growth:
2.1K
Growth Rate:
46.09%
Total runs:
4.1K
Run Growth:
1.6K
Growth Rate:
40.45%
Total runs:
3.9K
Run Growth:
230
Growth Rate:
6.03%
Total runs:
3.8K
Run Growth:
749
Growth Rate:
19.79%
Total runs:
3.7K
Run Growth:
-116
Growth Rate:
-3.15%
Total runs:
2.5K
Run Growth:
2.2K
Growth Rate:
86.83%
Total runs:
1.9K
Run Growth:
375
Growth Rate:
21.00%
Total runs:
1.7K
Run Growth:
814
Growth Rate:
49.54%
Total runs:
1.3K
Run Growth:
-233
Growth Rate:
-18.71%
Total runs:
1.1K
Run Growth:
-3
Growth Rate:
-0.28%
Total runs:
1.0K
Run Growth:
315
Growth Rate:
30.67%
Total runs:
926
Run Growth:
110
Growth Rate:
12.44%
Total runs:
878
Run Growth:
-716
Growth Rate:
-83.26%
Total runs:
785
Run Growth:
-753
Growth Rate:
-95.92%
Total runs:
629
Run Growth:
-1.0K
Growth Rate:
-142.80%
Total runs:
612
Run Growth:
430
Growth Rate:
70.26%
Total runs:
591
Run Growth:
302
Growth Rate:
51.19%
Total runs:
516
Run Growth:
242
Growth Rate:
46.90%
Total runs:
483
Run Growth:
-144
Growth Rate:
-33.33%
Total runs:
452
Run Growth:
138
Growth Rate:
37.30%
Total runs:
445
Run Growth:
24
Growth Rate:
5.31%
Total runs:
438
Run Growth:
274
Growth Rate:
57.32%
Total runs:
274
Run Growth:
-32
Growth Rate:
-11.90%
Total runs:
256
Run Growth:
142
Growth Rate:
55.47%
Total runs:
248
Run Growth:
-75
Growth Rate:
-31.51%
Total runs:
220
Run Growth:
141
Growth Rate:
64.98%
Total runs:
213
Run Growth:
86
Growth Rate:
40.95%
Total runs:
193
Run Growth:
136
Growth Rate:
70.47%
Total runs:
185
Run Growth:
161
Growth Rate:
87.03%
Total runs:
183
Run Growth:
-693
Growth Rate:
-238.97%
Total runs:
183
Run Growth:
-55
Growth Rate:
-32.35%
Total runs:
178
Run Growth:
124
Growth Rate:
72.94%
Total runs:
169
Run Growth:
134
Growth Rate:
84.28%
Total runs:
166
Run Growth:
51
Growth Rate:
30.72%
Total runs:
150
Run Growth:
-36
Growth Rate:
-25.35%
Total runs:
146
Run Growth:
139
Growth Rate:
95.21%
Total runs:
138
Run Growth:
66
Growth Rate:
47.83%
Total runs:
130
Run Growth:
110
Growth Rate:
89.43%
Total runs:
130
Run Growth:
-167
Growth Rate:
-129.46%
Total runs:
130
Run Growth:
85
Growth Rate:
66.41%
Total runs:
113
Run Growth:
57
Growth Rate:
57.00%
Total runs:
111
Run Growth:
75
Growth Rate:
67.57%
Total runs:
109
Run Growth:
65
Growth Rate:
60.19%
Total runs:
103
Run Growth:
-60
Growth Rate:
-60.61%
Total runs:
103
Run Growth:
-63
Growth Rate:
-56.76%
Total runs:
97
Run Growth:
4
Growth Rate:
10.53%
Total runs:
75
Run Growth:
-30
Growth Rate:
-54.55%
Total runs:
72
Run Growth:
20
Growth Rate:
27.78%
Total runs:
59
Run Growth:
-19
Growth Rate:
-32.20%
Total runs:
59
Run Growth:
56
Growth Rate:
94.92%