Total runs:
12.0M
Run Growth:
4.6M
Growth Rate:
38.60%
Sponsored by
APIMart
apple / aimv2-large-patch14-336
Model's Last Updated: July 09 2025
image-feature-extraction
Introduction of aimv2-large-patch14-336
Model Details of aimv2-large-patch14-336
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-patch14-336",
)
model = AutoModel.from_pretrained(
"apple/aimv2-large-patch14-336",
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-patch14-336",
)
model = FlaxAutoModel.from_pretrained(
"apple/aimv2-large-patch14-336",
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-patch14-336 on huggingface.co
203
Total runs
49
24-hour runs
66
3-day runs
83
7-day runs
149
30-day runs
More Information About aimv2-large-patch14-336 huggingface.co Model
Url of aimv2-large-patch14-336
aimv2-large-patch14-336 huggingface.co Url
Provider of aimv2-large-patch14-336 huggingface.co
Other API from apple
Updated:March 01 2025
Total runs:
2.4M
Run Growth:
-497.9K
Growth Rate:
-21.12%
Total runs:
1.6M
Run Growth:
-10.9K
Growth Rate:
-0.71%
Total runs:
1.2M
Run Growth:
-630.2K
Growth Rate:
-49.92%
Total runs:
141.3K
Run Growth:
112.4K
Growth Rate:
79.69%
Total runs:
88.9K
Run Growth:
-30.3K
Growth Rate:
-35.42%
Total runs:
10.4K
Run Growth:
4.8K
Growth Rate:
45.48%
Total runs:
8.2K
Run Growth:
5.8K
Growth Rate:
71.61%
Total runs:
7.6K
Run Growth:
-6.8K
Growth Rate:
-90.08%
Total runs:
4.7K
Run Growth:
1.8K
Growth Rate:
38.03%
Total runs:
4.6K
Run Growth:
2.8K
Growth Rate:
61.37%
Total runs:
4.4K
Run Growth:
2.1K
Growth Rate:
46.45%
Total runs:
4.0K
Run Growth:
1.8K
Growth Rate:
40.46%
Total runs:
3.9K
Run Growth:
159
Growth Rate:
3.95%
Total runs:
3.7K
Run Growth:
-263
Growth Rate:
-6.92%
Total runs:
2.0K
Run Growth:
2.0K
Growth Rate:
92.63%
Total runs:
1.7K
Run Growth:
292
Growth Rate:
16.81%
Total runs:
1.4K
Run Growth:
538
Growth Rate:
37.36%
Total runs:
1.3K
Run Growth:
-104
Growth Rate:
-8.01%
Total runs:
1.0K
Run Growth:
-57
Growth Rate:
-4.73%
Total runs:
1.0K
Run Growth:
274
Growth Rate:
26.35%
Total runs:
967
Run Growth:
-114
Growth Rate:
-11.70%
Total runs:
847
Run Growth:
-491
Growth Rate:
-58.45%
Total runs:
795
Run Growth:
-943
Growth Rate:
-119.07%
Total runs:
557
Run Growth:
202
Growth Rate:
35.82%
Total runs:
546
Run Growth:
334
Growth Rate:
62.08%
Total runs:
506
Run Growth:
156
Growth Rate:
31.08%
Total runs:
469
Run Growth:
287
Growth Rate:
61.19%
Total runs:
397
Run Growth:
123
Growth Rate:
30.98%
Total runs:
382
Run Growth:
-441
Growth Rate:
-108.09%
Total runs:
378
Run Growth:
497
Growth Rate:
98.22%
Total runs:
374
Run Growth:
-162
Growth Rate:
-41.43%
Total runs:
356
Run Growth:
118
Growth Rate:
33.71%
Total runs:
260
Run Growth:
48
Growth Rate:
18.82%
Total runs:
256
Run Growth:
77
Growth Rate:
30.08%
Total runs:
254
Run Growth:
-153
Growth Rate:
-61.69%
Total runs:
209
Run Growth:
50
Growth Rate:
24.04%
Total runs:
208
Run Growth:
113
Growth Rate:
54.85%
Total runs:
189
Run Growth:
108
Growth Rate:
54.00%
Total runs:
188
Run Growth:
-173
Growth Rate:
-94.02%
Total runs:
177
Run Growth:
164
Growth Rate:
91.11%
Total runs:
165
Run Growth:
105
Growth Rate:
64.81%
Total runs:
159
Run Growth:
-179
Growth Rate:
-111.88%
Total runs:
154
Run Growth:
137
Growth Rate:
88.39%
Total runs:
146
Run Growth:
130
Growth Rate:
89.04%
Total runs:
138
Run Growth:
66
Growth Rate:
47.83%
Total runs:
124
Run Growth:
75
Growth Rate:
60.48%
Total runs:
119
Run Growth:
103
Growth Rate:
86.55%
Total runs:
115
Run Growth:
-51
Growth Rate:
-44.74%
Total runs:
113
Run Growth:
78
Growth Rate:
67.24%
Total runs:
110
Run Growth:
68
Growth Rate:
62.96%
Total runs:
105
Run Growth:
61
Growth Rate:
61.00%
Total runs:
93
Run Growth:
-73
Growth Rate:
-79.35%
Total runs:
63
Run Growth:
-34
Growth Rate:
-50.75%
Total runs:
58
Run Growth:
-64
Growth Rate:
-110.34%
Total runs:
57
Run Growth:
23
Growth Rate:
37.70%
Total runs:
56
Run Growth:
51
Growth Rate:
91.07%
Total runs:
46
Run Growth:
-92
Growth Rate:
-200.00%