ModelListedExternal

Siglip2 Vision Only

This is the vision-only variant of google/siglip2-base-patch16-224, containing just the vision encoder without the text model.

Sourcehuggingface.co/Hayloo9838/siglip2-vision-only/tree/b40dce96dc810c59eab7ac770d0d46f9db9292f6

KindCLIP visionBase modelgoogle/siglip2-base-patch16-224Versionpytorch_modelBgrade

Model source

Kind: CLIP vision
File size: 354 MB
Base model: google/siglip2-base-patch16-224
Version: vpytorch_model
Updated: Oct 13, 2026
Downloads: 5
Source: Hugging Face

Source description

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.

Sources

1 source

Hugging FacePrimaryVersion b40dce96dc810c59eab7ac770d0d46f9db9292f6

huggingface.co/Hayloo9838/siglip2-vision-only/tree/b40dce96dc810c59eab7ac770d0d46f9db9292f6

Verified Aug 26

Model artifacts

1 artifact

pytorch_model.bin

bin · 354 MB · SHA-256 2ab27fe14945…59e5 · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeAug 26huggingface.co/Hayloo9838/siglip2-vision-only

--- license: apache-2.0 language: - en base_model: - google/siglip2-base-patch16-224 tags: - vision - image-feature-extraction - siglip - siglip2 library_name: transformers pipeline_tag: image-feature-extraction --- # SigLIP-2 Vision Encoder (Base, Patch 16x16, 224px) This is the **vision-only** variant of [google/siglip2-base-patch16-224](https://huggingface.co/google/siglip2-base-patch16-224), containing just the vision encoder without the text model.

NoteAug 26huggingface.co/Hayloo9838/siglip2-vision-only

Source context: 5 downloads · 0 likes · Pipeline image-feature-extraction · Library transformers · Repo Hayloo9838/siglip2-vision-only