Google's TIPS v2 (SO400M/14) is a contrastive vision-language model supporting zero-shot image classification and feature extraction. The model is published on Hugging Face with full weights and can be used via the Transformers library for various multimodal computer vision tasks.
Tipsv2 So400m14 is an Other AI product. It focuses on performing zero-shot image classification and retrieval without task-specific training data. Tipsv2 So400m14 is an open-source project aimed at computer vision developers. The project is open source (Apache-2.0). The product ships for the web, the command line, and API.
It is developed by Google (United States), and the product first shipped in 2025. The project is developed in the open on GitHub with 572 stars and 23 commits in the last 90 days. Among its 3 catalogued features are Zero-Shot Classification, Vision-Language Model, and Contrastive Learning.
Latest indexed changes and source events
google/tipsv2-so400m14 verified by the PulseGate indexer
