google/siglip2-giant-opt-patch16-384

Zero Shot Image Classification·google· 962.4K· 43

transformers apache-2.0 1.9B params arxiv:2502.14786arxiv:2303.15343arxiv:2209.06794license:apache-2.0region:us

SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved semantic understanding, localization, and dense features.

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull google/siglip2-giant-opt-patch16-384

Model details

Task

Zero Shot Image Classification

Provider

google

Framework

transformers

Parameters

1.9B

Size

7.0 GB

License

apache-2.0

Downloads

962.4K

Likes

Paper

arXiv:2502.14786

Updated

2025-02-21

About google/siglip2-giant-opt-patch16-384

SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved semantic understanding, localization, and dense features.

Related Zero Shot Image Classification

C openai/clip-vit-base-patch32 Zero Shot Image Classification 22.8M 966 🤗 HF C openai/clip-vit-large-patch14 Zero Shot Image Classification ·427.6M params 12.0M 2.0K 🤗 HF C laion/CLIP-ViT-B-32-laion2B-s34B-b79K Zero Shot Image Classification ·151.3M params 3.8M 141 🤗 HF P yuvalkirstain/PickScore_v1 Zero Shot Image Classification ·986.1M params 3.2M 52 🤗 HF F patrickjohncyh/fashion-clip Zero Shot Image Classification ·151.3M params 2.9M 284 🤗 HF C openai/clip-vit-large-patch14-336 Zero Shot Image Classification 2.8M 308 🤗 HF