This is an open-weight CLIP model that pairs a ConvNeXt image encoder with a text encoder, trained on the LAION-2B dataset. It supports zero-shot image classification, image-text similarity, and retrieval tasks. The model can be used locally through Hugging Face libraries or via hosted inference endpoints.
CLIP Convnext Base W laion2B s13B b82K Augreg is a Multimodal & vision project. It focuses on enabling zero-shot image classification and retrieval without task-specific training data. It is built as an open-source project for developers. CLIP Convnext Base W laion2B s13B b82K Augreg is open source under the Open Source license. It ships for the web and API.
Behind CLIP Convnext Base W laion2B s13B b82K Augreg is LAION, and it first shipped in 2021. The project is developed in the open on GitHub with 14k stars and 104 commits in the last 90 days. PulseGate's similarity index places it among 5 comparable projects. Key capabilities include Zero-Shot Classification, Image-Text Retrieval, and ConvNeXt Backbone.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do