# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Hayloo9838/siglip2-vision-only", device_map="auto")Quick Links
Configuration Parsing Warning:In config.json: "architectures" must be an array
SigLIP-2 Vision Encoder (Base, Patch 16x16, 224px)
This is the vision-only variant of google/siglip2-base-patch16-224, containing just the vision encoder without the text model.
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Hayloo9838/siglip2-vision-only
Base model
google/siglip2-base-patch16-224
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="Hayloo9838/siglip2-vision-only")