Downloads · 30 days
273
21% of all-time downloads
siglip2-base-p32-256-ve
jingyaogong/siglip2-base-p32-256-ve
siglip2-base-p32-256-ve is a machine learning model from jingyaogong. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
All-time downloads
1.3K
Public
Parameters
94.6M
904 MB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors189 MB · 100%
At a glance
- License
- apache-2.0
- Model type
- siglip_vision_model
- Access
- Public
- Created
- Feb 7, 2026
- Updated
- Apr 20, 2026
- SHA
- 9465d1dc
Base models
Model card
From the Hugging Face model README
SigLIP2 ViT-B/32 Vision Encoder (256)
模型来源：google/siglip2-base-patch32-256
仅裁剪保留了 Vision Encoder 部分，去除了 Text Encoder 及其他无关权重，并以 float16 精度保存为 HuggingFace SiglipVisionModel 兼容的 safetensors 格式。
Source: google/siglip2-base-patch32-256
Only the Vision Encoder is retained. The Text Encoder and all unrelated weights have been removed. Weights are saved in float16 precision as HuggingFace SiglipVisionModel-compatible safetensors format.
Model Info
| Item | Value |
|---|---|
| Architecture | SigLIP2 ViT-B/32 (fixed resolution) |
| Parameters | 94.6M |
| Hidden Size | 768 |
| Layers | 12 |
| Patch Size | 32 |
| Input Resolution | 256×256 |
| Output Tokens | 64 (8×8) |
| Weight Precision | float16 |
| File Size | ~180MB |
Usage
from transformers import SiglipVisionModel, SiglipImageProcessor
model = SiglipVisionModel.from_pretrained("path_to/siglip2-base-p32-256-ve")
processor = SiglipImageProcessor.from_pretrained("path_to/siglip2-base-p32-256-ve")
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs) # outputs.last_hidden_state: [B, 64, 768]
- Type
- siglip_vision_model
- License
- apache-2.0
- Languages
- zh, en
- Created
- Feb 7, 2026
- Updated
- Apr 20, 2026