Total runs:
1.6K
Run Growth:
29
Growth Rate:
1.80%
Sponsored by
APIMaster
alphaedge-ai / siglip2-base-patch16-512-deu-32768
Model's Last Updated: July 15 2026
zero-shot-image-classification
Introduction of siglip2-base-patch16-512-deu-32768
Model Details of siglip2-base-patch16-512-deu-32768
siglip2-base-patch16-512-deu-32768
This model is a
45.62%
smaller version of
google/siglip2-base-patch16-512
optimized for
German
language via vocabulary size reduction using the
trimming
method.
This trimmed model should perform similarly to the original model with only 32,768 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected languages were removed from the vocabulary.
Model Statistics
| Metric | Original | Trimmed | Reduction |
|---|---|---|---|
| Vocabulary size | 256,000 tokens | 32,768 tokens | 87.20% |
| Model size | 375,823,874 params | 204,381,698 params | 45.62% |
Mining Dataset Statistics
- Number of texts used for mining : 200,000 texts
- Dataset : lbourdois/fineweb-2-trimming
Usage
Transformers (zero-shot image classification)
from transformers import pipeline
# load pipeline
image_classifier = pipeline(model="alphaedge-ai/siglip2-base-patch16-512-deu-32768", task="zero-shot-image-classification")
# load image and candidate labels
image = "http://images.cocodataset.org/val2017/000000039769.jpg"
candidate_labels = ["Potential label 1 in German", "Potential label 2 in German", "Potential label 3 in German", "Potential label 4 in German"]
# run inference
outputs = image_classifier(image, candidate_labels)
print(outputs)
Sentence-transformers (texts-images similarity)
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("alphaedge-ai/siglip2-base-patch16-512-deu-32768")
images = [
"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
"https://huggingface.co/datasets/huggingface/cats-image/resolve/main/cats_image.jpeg"
]
texts = ["Text 1 in German", "Text 2 in German", "Text 3 in German", "Text 4 in German"]
image_embeddings = model.encode(images)
text_embeddings = model.encode(texts)
print(image_embeddings.shape, text_embeddings.shape)
similarities = model.similarity(image_embeddings, text_embeddings)
print(similarities)
Citations
SigLIP 2
@misc{tschannen2025siglip2multilingualvisionlanguage,
title={SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features},
author={Michael Tschannen and Alexey Gritsenko and Xiao Wang and Muhammad Ferjad Naeem and Ibrahim Alabdulmohsin and Nikhil Parthasarathy and Talfan Evans and Lucas Beyer and Ye Xia and Basil Mustafa and Olivier Hénaff and Jeremiah Harmsen and Andreas Steiner and Xiaohua Zhai},
year={2025},
eprint={2502.14786},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2502.14786},
}
Trimming blog post
@misc{hf_blogpost_trimming,
title={Introduction to Trimming},
author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
year={2026},
url={https://huggingface.co/blog/lbourdois/introduction-to-trimming},
}
Runs of alphaedge-ai siglip2-base-patch16-512-deu-32768 on huggingface.co
203
Total runs
0
24-hour runs
1
3-day runs
1
7-day runs
197
30-day runs
More Information About siglip2-base-patch16-512-deu-32768 huggingface.co Model
Url of siglip2-base-patch16-512-deu-32768
siglip2-base-patch16-512-deu-32768 huggingface.co Url
Provider of siglip2-base-patch16-512-deu-32768 huggingface.co
Other API from alphaedge-ai
Updated:May 20 2026
Total runs:
854
Run Growth:
848
Growth Rate:
99.30%
Total runs:
458
Run Growth:
207
Growth Rate:
45.20%
Total runs:
399
Run Growth:
374
Growth Rate:
93.73%
Total runs:
236
Run Growth:
200
Growth Rate:
84.75%
Total runs:
224
Run Growth:
219
Growth Rate:
97.77%
Total runs:
214
Run Growth:
-43
Growth Rate:
-20.09%
Total runs:
214
Run Growth:
124
Growth Rate:
57.94%
Total runs:
208
Run Growth:
131
Growth Rate:
62.98%
Total runs:
152
Run Growth:
78
Growth Rate:
51.32%
Total runs:
127
Run Growth:
116
Growth Rate:
91.34%
Total runs:
118
Run Growth:
24
Growth Rate:
20.34%
Total runs:
112
Run Growth:
14
Growth Rate:
12.50%
Total runs:
108
Run Growth:
37
Growth Rate:
34.26%
Total runs:
106
Run Growth:
12
Growth Rate:
11.32%
Total runs:
105
Run Growth:
18
Growth Rate:
17.14%
Total runs:
105
Run Growth:
94
Growth Rate:
89.52%
Total runs:
105
Run Growth:
96
Growth Rate:
91.43%
Total runs:
104
Run Growth:
34
Growth Rate:
32.69%
Total runs:
103
Run Growth:
33
Growth Rate:
31.73%
Total runs:
102
Run Growth:
28
Growth Rate:
27.45%
Total runs:
101
Run Growth:
22
Growth Rate:
21.78%
Total runs:
100
Run Growth:
29
Growth Rate:
29.00%
Total runs:
100
Run Growth:
27
Growth Rate:
27.00%
Total runs:
100
Run Growth:
30
Growth Rate:
30.00%
Total runs:
100
Run Growth:
90
Growth Rate:
90.00%
Total runs:
100
Run Growth:
13
Growth Rate:
13.00%
Total runs:
100
Run Growth:
14
Growth Rate:
14.00%
Total runs:
99
Run Growth:
6
Growth Rate:
6.06%
Total runs:
99
Run Growth:
-71
Growth Rate:
-71.72%
Total runs:
99
Run Growth:
12
Growth Rate:
12.12%
Total runs:
99
Run Growth:
12
Growth Rate:
12.12%
Total runs:
99
Run Growth:
8
Growth Rate:
8.08%
Total runs:
99
Run Growth:
13
Growth Rate:
13.13%
Total runs:
99
Run Growth:
8
Growth Rate:
8.08%
Total runs:
98
Run Growth:
89
Growth Rate:
90.82%
Total runs:
98
Run Growth:
21
Growth Rate:
21.43%
Total runs:
98
Run Growth:
27
Growth Rate:
27.55%
Total runs:
98
Run Growth:
10
Growth Rate:
10.20%
Total runs:
98
Run Growth:
25
Growth Rate:
25.51%
Total runs:
97
Run Growth:
7
Growth Rate:
7.22%
Total runs:
95
Run Growth:
27
Growth Rate:
28.13%
Total runs:
95
Run Growth:
4
Growth Rate:
4.21%
Total runs:
95
Run Growth:
26
Growth Rate:
27.08%
Total runs:
95
Run Growth:
13
Growth Rate:
13.68%
Total runs:
94
Run Growth:
24
Growth Rate:
25.53%
Total runs:
93
Run Growth:
23
Growth Rate:
24.47%
Total runs:
93
Run Growth:
3
Growth Rate:
3.23%
Total runs:
93
Run Growth:
-3
Growth Rate:
-3.23%
Total runs:
93
Run Growth:
1
Growth Rate:
1.08%
Total runs:
93
Run Growth:
83
Growth Rate:
89.25%
Total runs:
93
Run Growth:
24
Growth Rate:
25.81%
Total runs:
92
Run Growth:
4
Growth Rate:
4.35%
Total runs:
92
Run Growth:
21
Growth Rate:
22.83%
Total runs:
92
Run Growth:
22
Growth Rate:
23.91%
Total runs:
92
Run Growth:
24
Growth Rate:
26.09%
Total runs:
92
Run Growth:
9
Growth Rate:
9.78%
Total runs:
92
Run Growth:
12
Growth Rate:
13.04%
Total runs:
92
Run Growth:
10
Growth Rate:
10.87%
Total runs:
91
Run Growth:
20
Growth Rate:
21.98%
Total runs:
91
Run Growth:
0
Growth Rate:
0.00%
Total runs:
91
Run Growth:
14
Growth Rate:
15.38%
Total runs:
90
Run Growth:
18
Growth Rate:
20.00%
Total runs:
90
Run Growth:
6
Growth Rate:
6.67%
Total runs:
90
Run Growth:
22
Growth Rate:
24.44%
Total runs:
90
Run Growth:
3
Growth Rate:
3.33%
Total runs:
90
Run Growth:
-5
Growth Rate:
-5.56%
Total runs:
90
Run Growth:
18
Growth Rate:
20.00%
Total runs:
90
Run Growth:
-9
Growth Rate:
-10.00%
Total runs:
90
Run Growth:
9
Growth Rate:
9.89%
Total runs:
90
Run Growth:
23
Growth Rate:
25.56%
Total runs:
90
Run Growth:
-37
Growth Rate:
-41.11%
Total runs:
90
Run Growth:
82
Growth Rate:
91.11%
Total runs:
90
Run Growth:
19
Growth Rate:
20.88%
Total runs:
90
Run Growth:
3
Growth Rate:
3.33%
Total runs:
90
Run Growth:
22
Growth Rate:
24.44%
Total runs:
90
Run Growth:
-1
Growth Rate:
-1.11%
Total runs:
90
Run Growth:
21
Growth Rate:
22.83%
Total runs:
89
Run Growth:
16
Growth Rate:
17.98%
Total runs:
89
Run Growth:
79
Growth Rate:
88.76%
Total runs:
89
Run Growth:
9
Growth Rate:
10.11%