tipsv2-b14 is a Google research model for zero-shot image classification using contrastive learning between images and text. It supports feature extraction and vision-language tasks and is distributed on Hugging Face for use with the Transformers library.
Tipsv2 B14 sits in PulseGate's Other AI category. It focuses on performing zero-shot image classification and multimodal feature extraction without task-specific training. Tipsv2 B14 is an open-source project aimed at developers. The project is open source (Apache-2.0). The product ships for the web and the command line.
Google builds and maintains Tipsv2 B14, and the product first shipped in 2025. The project is developed in the open on GitHub with 571 stars and 24 commits in the last 90 days. Among its 3 catalogued features are Zero-shot Classification, Contrastive Learning, and vision-Language.
Latest indexed changes and source events
google/tipsv2-b14 verified by the PulseGate indexer
Other apps tracked under the same category.
